# SimplaDocs — Full Content Corpus > Inlined markdown of every public page on simpladocs.com. Auto-generated; the canonical HTML lives at the URL noted under each entry. SimplaDocs is an AI-native operational transformation consultancy — the #1 Expert Partner for Coda, Superhuman Docs, and Superhuman Go. # Operations built to scale — *with AI, agents, and the right tools.* > SimplaDocs is an AI-native operational transformation consultancy — the #1 Expert Partner for Coda, Superhuman Docs, and Superhuman Go — trusted by 200+ companies including Spotify, Netflix, Fidelity, and Qualtrics, having completed 215+ projects and saved clients 83,000+ hours. ## Hero We're an operational transformation consultancy that consults AND builds. Tool-agnostic by default; deepest specialty in Coda, Superhuman Docs, and Superhuman Go — where we're the #1 Expert Partner. **CTA:** Let's Talk → /contact *#1 implementation partner for Superhuman + Coda* --- ## Trusted By Loved by 100+ teams and growing brands around the world — including Spotify, Netflix, Fidelity, MrBeast, Qualtrics, DoorDash, and EA Games. --- ## What We Do Custom solutions that scale with your business — from simple workflows to complete operations. ### Automation ### Visibility ### Scale --- ## Why SimplaDocs? - **+215** Total Projects Completed - **+15** Years of Experience - **+83k** Hours of Work Saved ### Coda Partners We work directly with Coda (now rebranding as Superhuman Docs), stay ahead of new features and capabilities, and bring deep platform expertise to every project. ### Our Founder Our founder, Scott Collier-Weir (The Coda Guy), is a recognized leader in the Coda community, with thousands of followers learning from his YouTube tutorials. ### We Want to Get to Know You We spend the time to understand how you work and what solutions feel intuitive for your team. Every doc is custom-built for your specific workflows. ### Low Maintenance We create straightforward solutions that your team can understand and adapt internally — no black boxes, no technical dependencies, and no over-engineered solutions. ### Discovery + Building, Together We pair discovery with rapid prototyping for quick iteration and fast turnaround times. ### Flexible Partnership Models We right-size our support based on your business needs: one-off projects, full-scale overhauls, ongoing retainers, and everything in between. --- ## How We Help ### Custom Solutions We build what your business needs: hiring and onboarding trackers, budget and spend management, project dashboards, sales CRMs, inventory systems, and operational hubs — all designed around how your team actually works. ### Workflow Automation We automate what slows you down: data entry and updates, email notifications and reminders, cross-tool syncing, approval workflows, report generation, and task assignments — so your team can focus on high-value work. ### Operational Visibility We unify what matters most: real-time performance dashboards, budget and spend tracking, project status and timelines, team capacity and workload, KPI monitoring, and cross-functional reporting. ### End-to-End Partnership We support you from start to scale: initial discovery and requirements gathering, custom system design and buildout, team training and onboarding, ongoing optimization and updates. --- ## Our Methodology: the Value Chain Every engagement follows the same four-stage progression — so you always know where you are and what comes next. ### 01 — Assess Map workflows, diagnose readiness, and surface what's blocking AI adoption. ### 02 — Structure Organize the content, knowledge, and guardrails AI needs to succeed. ### 03 — Enable Train teams and onboard AI tools alongside them — adoption before deployment. ### 04 — Deploy Build and maintain the agents and tools that make change real, with measurable ROI. --- ## Everything your team needs to scale - Expert Consultants — Our team of foremost Coda / Superhuman Docs developers architects and builds custom solutions for your business. - AI Context Engineering — Leverage AI to structure and enrich your operational context for smarter automations. - Coda Packs — Coda plus your favorite tools equals operational gold. We build packs that connect it all. - Coda Admin as a Service — No dedicated IT team for system admin? We handle the day-to-day so you don't have to. - Workspace Health Report — Performance is everything. We get your docs in peak form so your team can move faster. - Coda School — Self-paced Coda training for DIYers, paired with 1:1 expert support and a learning community. - Doc Review — Already use Coda but need a tune-up? A low-commitment review to point you in the right direction. - Templates — Not sure where to start? Explore our ready-made templates and hit the ground running. **CTA:** Let's Build Something That Works → [Let's Talk](/contact) | [View Our Work](/#work) --- ## How our systems turned chaos into clarity ### "No backfill needed after PM retired" Operational Excellence · Leading Engineering Consultancy · Tags: Automation, Coda Pack ### "Single source of truth for 20+ teams" Smarter Budgeting · Global Management Consultancy · Tags: Budgeting, Dashboards ### "11x faster workflows, 250+ hours saved" Scalable Systems · U.S. State Environmental Agency · Tags: Process Automation, Forms ### "Best investment of 2023" Fractional CTO · Bipty · Tags: Fractional CTO, Pack Creation --- ## Meet the creative minds behind our success - **Scott Collier-Weir** — Founder & Lead Consultant - **Steven Hurtado Roldan** — Director of Business Strategy & AI - **Jordyn Goffo** — Project Manager & Operations Lead - **Rachel** — Head of Sales [Meet our whole team →](/team) | [See open positions →](/careers) --- ## What our satisfied customers are saying about us > "As a CIO, I've worked with many many vendors, and SimplaDocs was the best ROI I've ever made." > — Government CIO, U.S. State Environmental Agency > "SimplaDocs has been an incredible partner to the Qualtrics Research Services organization. They bring platform expertise, solutions focused thinking, and flexibility to every engagement." > — Mark Masterton, Director of Research Services, Qualtrics > "This is easily the best money we are spending every month... SimplaDocs has helped simplify weeks of work into one simple click of a button... It's one person doing the job of at least three after the automations." > — Kaspar Povilanskas, Co-Founder, Nowadays Media **Facts & Numbers:** 91% of clients recommend our operations services. --- ## Got questions? We've got answers **What is Coda and why do you use it?** Coda is an all-in-one doc that combines documents, spreadsheets, and applications. We use it because it's incredibly flexible, easy for teams to adopt, and powerful enough to replace multiple tools in your stack. **How long does a typical project take?** Most projects are delivered in 2-6 weeks depending on complexity. Simple automations can be live in days, while full operational systems take a few weeks to design, build, and roll out. **What does onboarding look like?** We start with a discovery call to understand your current workflows and pain points. Then we design a solution, build it iteratively with your feedback, and train your team before handoff. **Do you offer ongoing support?** Yes! We offer monthly support plans that include optimization, troubleshooting, and new feature development as your needs evolve. **What size teams do you work with?** We work with teams of all sizes — from 5-person startups to 500+ person organizations. Our solutions scale to match your team's complexity. **Can you integrate with our existing tools?** Absolutely. Coda integrates with Slack, Google Workspace, Jira, Salesforce, and hundreds of other tools. We'll make sure your new system fits seamlessly into your existing workflow. --- ## Let's Build Something That Works Tell us what you need — we'll show you what's possible. **CTA:** Let's Talk → /contact --- ## Related - [Our Services](https://simpladocs.com/services) - [Our Work / Case Studies](https://simpladocs.com/work) - [About SimplaDocs](https://simpladocs.com/about) - [Our Process](https://simpladocs.com/our-process) - [Contact Us](https://simpladocs.com/contact) - [Coda Expert Partner Consultancy](https://simpladocs.com/coda-consultants) --- *Source: https://simpladocs.com/* — last reviewed 2026-05-04 # Our Services > SimplaDocs is an operational transformation consultancy that consults AND builds — offering eight service packages across the Value Chain methodology (Assess → Structure → Enable → Deploy), with tool-agnostic delivery and deepest specialty in Coda, Superhuman Docs, and Superhuman Go. ## We consult AND build. Our service packages each map to one or more stages of our **Value Chain methodology** (Assess → Structure → Enable → Deploy). Tool-agnostic by default; deepest specialty in Coda, Superhuman Docs, and Superhuman Go. --- ## Our Methodology: The Value Chain Every engagement maps to one or more stages: ### 01 — Assess Map workflows, diagnose readiness, surface what's blocking AI adoption. ### 02 — Structure Organize the content, knowledge, and guardrails AI needs to succeed. ### 03 — Enable Train teams and onboard AI tools alongside them — adoption before deployment. ### 04 — Deploy Build and maintain the agents and tools that make change real, with measurable ROI. --- ## Service Packages ### Expert Consultants Access seasoned Coda / Superhuman Docs experts who understand your business needs and can architect the perfect solution. Our team of foremost developers builds custom solutions tailored to your business workflows. *Value Chain stages: Assess, Structure, Deploy* ### AI Context Engineering Leverage AI to enhance your workflows with intelligent automation and context-aware solutions. AI-powered operational automation built natively on Coda and Superhuman. *Value Chain stages: Structure, Deploy* ### Coda Packs Custom integrations connecting Coda with your existing tools. Coda plus your favorite tools equals operational gold. We build packs that connect it all. 110+ Packs built, 15+ included in Coda's official enterprise bundle. *Value Chain stage: Deploy* ### Coda Admin as a Service Ongoing workspace management, maintenance, and optimization handled by our expert team. No dedicated IT team for system admin? We handle the day-to-day so you don't have to. *Value Chain stage: Enable, Deploy* ### Workspace Health Report A thorough audit of your Coda workspace covering performance, structure, and security insights. Performance is everything. We get your docs in peak form so your team can move faster. *Value Chain stage: Assess* ### Coda School Training programs that empower your team to become Coda power users and self-sufficient builders. Self-paced Coda training for DIYers, paired with 1:1 expert support and a learning community. *Value Chain stage: Enable* ### Doc Review Get a comprehensive review of your existing Coda docs with actionable recommendations for improvement. Already use Coda but need a tune-up? A low-commitment review to point you in the right direction. *Value Chain stage: Assess* ### Templates Pre-built, customizable Coda templates designed for common business workflows and use cases. Not sure where to start? Explore our ready-made templates and hit the ground running. *Value Chain stage: Structure* --- ## Need a Custom Solution? Every team is different. Let us design a service package tailored to your specific needs. **CTA:** [Get in Touch](/contact) --- ## Topic Owners - **Scott Collier-Weir** — Coda / Superhuman Docs / Superhuman Go specialist, Expert Consultants, Coda Packs - **Steven Hurtado Roldan** — AI strategy, AI Context Engineering, methodology - **Jordyn Goffo** — Project management, consulting delivery, operations improvement - **Daniel Velho** — Coda expertise, enterprise delivery, Admin as a Service - **Rachel** — AI-improved sales, content distribution ## Related - [Our Process](https://simpladocs.com/our-process) - [Our Work / Case Studies](https://simpladocs.com/work) - [Coda Expert Partner Consultancy](https://simpladocs.com/coda-consultants) - [Contact Us](https://simpladocs.com/contact) --- *Source: https://simpladocs.com/services* — last reviewed 2026-05-04 # Our Work > SimplaDocs has delivered 215+ operational transformation projects for 200+ companies — turning workflow chaos into measurable clarity, with results including 11x faster workflows, 250+ hours saved, and clients calling us "the best ROI I've ever made." ## Real results for real teams. See how we turn operational chaos into clarity. --- ## Case Studies ### "No backfill needed after PM retired" **Operational Excellence · Leading Engineering Consultancy** - Tags: Automation, Coda Pack - [View case study →](/work/engineering-consultancy) ### "Single source of truth for 20+ teams" **Smarter Budgeting · Global Management Consultancy** - Tags: Budgeting, Dashboards - [View case study →](/work/global-management-consultancy) ### "11x faster workflows, 250+ hours saved" **Scalable Systems · U.S. State Environmental Agency** - Tags: Process Automation, Forms - [View case study →](/work/state-environmental-agency) ### "Best investment of 2023" **Fractional CTO · Bipty** - Tags: Fractional CTO, Pack Creation - [View case study →](/work/bipty) ### "1 person doing the job of 3" **Campaign Automation · Nowadays Media** - Tags: Automation, Custom Pack - [View case study →](/work/nowadays-media) --- ## Industries We've Served - Technology - Finance - Government - Media & Advertising - Entertainment - Management Consulting - Engineering From 5-person startups to Fortune 500 enterprises. Clients include: Spotify, Netflix, Fidelity, MrBeast, Qualtrics, DoorDash, EA Games, and 200+ more. --- ## Related - [Our Services](https://simpladocs.com/services) - [Contact Us](https://simpladocs.com/contact) - [Coda Expert Partner Consultancy](https://simpladocs.com/coda-consultants) - [About SimplaDocs](https://simpladocs.com/about) --- *Source: https://simpladocs.com/work* — last reviewed 2026-05-04 # Our Blog > The SimplaDocs blog publishes insights, guides, and updates on operations, automation, AI adoption, and building systems that scale — written by practitioners who build these systems for 200+ companies. ## Insights, guides, and updates on operations, automation, and building systems that scale. The SimplaDocs team writes about the practical realities of operational transformation: what works, what doesn't, and how to make AI and automation deliver real ROI for your business. --- ## Topics We Cover - Workflow automation and Coda best practices - AI adoption and context engineering - Operations strategy and methodology - Case studies and real-world results - Superhuman Docs and Superhuman Go product updates - No-code and low-code development --- ## About the Authors Content is written by the SimplaDocs team — practitioners who build operational systems every day for companies like Spotify, Netflix, Fidelity, and 200+ others. --- ## Related - [Our Services](https://simpladocs.com/services) - [Contact Us](https://simpladocs.com/contact) - [About SimplaDocs](https://simpladocs.com/about) --- *Source: https://simpladocs.com/blog* — last reviewed 2026-05-04 # About SimplaDocs > SimplaDocs is an AI-native operational transformation consultancy — the #1 Expert Partner for Coda and Superhuman Docs — founded in 2020 by Scott Collier-Weir (The Coda Guy), having served 200+ companies including Spotify, Netflix, and Fidelity across 215+ projects and 83,000+ hours saved. ## The #1 Coda Expert Partner consultancy — helping teams work smarter since 2020. --- ## Key Stats - **200+** Companies Served - **215+** Projects Completed - **110+** Coda Packs Built - **83k+** Hours Saved --- ## Our Story SimplaDocs is an **AI-native operational transformation consultancy**. We consult AND we build — embedding ourselves in operations to identify bottlenecks, structure the context AI needs to succeed, train teams to adopt new workflows, and deploy the agents and tools that make change real. Our deepest tool specialty is the Coda ecosystem — being rebranded as **Superhuman Docs** — and the new **Superhuman Go** agents product. We're the #1 Expert Partner for both. But the durable thing isn't a tool; it's our ability to transform how operations actually work. SimplaDocs started with a simple observation: businesses were drowning in disconnected spreadsheets, siloed tools, and manual processes that nobody had time to fix. Scott Collier-Weir — known in the Coda community as **The Coda Guy** — saw that Coda had the power to solve these problems, but most companies didn't know where to start. In 2020, he founded SimplaDocs to bridge that gap. What began as a one-person consultancy quickly grew as word spread: companies like Spotify, Netflix, Fidelity, and Qualtrics came to SimplaDocs to transform how their teams work. Each engagement reinforced the same lesson — the tool matters less than the thinking behind it. Today, SimplaDocs is the **#1 Coda Expert Partner** and the **#1 Superhuman implementation partner**. We've served over 200 companies across 215+ projects, saving clients more than 83,000 hours of manual work. Our team has built 110+ Coda Packs — more than any other builder — with 15+ included in Coda's official enterprise bundle. What sets SimplaDocs apart is our approach: we build solutions that teams can actually own. No black boxes, no vendor lock-in, no over-engineered systems. Just clear, maintainable operations infrastructure that scales with your business. --- ## Our Journey - **2020** — SimplaDocs Founded. Scott Collier-Weir launches SimplaDocs to help businesses unlock the full potential of Coda. - **2021** — First Major Enterprise Clients. SimplaDocs begins serving Fortune 500 companies including Spotify, Netflix, and Fidelity. - **2022** — Coda Expert Partner. Recognized as an official Coda Expert Partner — the highest tier in Coda's partner program. - **2023** — 100+ Coda Packs Built. Becomes the largest Coda Pack builder in the ecosystem, with 15+ Packs included in Coda's enterprise bundle. - **2024** — 200+ Companies Served. Crosses 200 clients, 215 projects, and 83,000 hours saved across industries worldwide. - **2025** — AI & Superhuman Expansion. Launches AI Context Engineering practice and becomes the #1 Superhuman implementation partner. --- ## Leadership ### Scott Collier-Weir — Founder & Lead Consultant ("The Coda Guy") Scott is a recognized leader in the Coda community, known for his YouTube tutorials that have helped thousands of people learn Coda. He founded SimplaDocs to bridge the gap between powerful no-code platforms and the operational challenges businesses face every day. Under his leadership, SimplaDocs has grown to serve 200+ companies including Spotify, Netflix, and Fidelity. ### Steven Hurtado Roldan — Director of Business Strategy & AI Steven leads SimplaDocs' AI practice and business strategy. A systems thinker and polymath, he translates complex problems into simple, working solutions. He heads the "AI No Jargon" initiative, making AI adoption practical and accessible for businesses. ### Daniel Velho — Senior Consultant Daniel is SimplaDocs' second hire, bringing deep Coda expertise and a client-first approach to every project. He leads complex enterprise engagements and is growing into a people leadership role within the team. [Meet the full team →](/team) --- ## Partnerships & Recognition ### Coda Expert Partner Official Expert Partner — the highest tier in Coda's partner program. SimplaDocs works directly with Coda on new features and capabilities. ### #1 Superhuman Partner The leading Superhuman implementation partner, helping companies deploy and optimize Superhuman for faster email workflows. ### Coda Enterprise Bundle 15+ SimplaDocs-built Packs are included in Coda's official enterprise bundle, used by thousands of companies worldwide. --- ## How We Work ### Build, Don't Slide We're operators, not presenters. Every engagement delivers working systems, not decks and recommendations. ### Clarity Over Cleverness We build solutions your team can understand, own, and evolve — no black boxes, no over-engineering. ### Discovery First We invest time understanding how you actually work before building anything. The right solution starts with the right questions. ### Partnership, Not Projects We think long-term. Our goal is to make your operations self-sustaining, whether through training, ongoing support, or both. [Read our mission →](/our-mission) | [See our process →](/our-process) --- ## Trusted by Industry Leaders From 5-person startups to Fortune 500 enterprises, SimplaDocs has delivered custom solutions across technology, finance, media, government, and consumer brands. Clients include: Spotify, Netflix, Fidelity, MrBeast, Qualtrics, DoorDash, EA Games — plus 200+ more companies across government, engineering, consulting, and media. --- ## Ready to Work Together? Whether you need a one-off build, a full-scale transformation, or an ongoing partnership — we'll find the right fit. **CTA:** [Let's Talk](/contact) | [See Our Work](/work) --- ## Topic Owners - **Scott Collier-Weir** — Coda / Superhuman Docs / Superhuman Go specialist, Founder - **Steven Hurtado Roldan** — AI strategy, business strategy, AI No Jargon - **Jordyn Goffo** — Operations improvement, consulting methodology, partnerships - **Daniel Velho** — Coda expertise, enterprise client delivery ## Related - [Our Mission](https://simpladocs.com/our-mission) - [Our Process](https://simpladocs.com/our-process) - [Our Team](https://simpladocs.com/team) - [Our Work](https://simpladocs.com/work) - [Coda Expert Partner Consultancy](https://simpladocs.com/coda-consultants) --- *Source: https://simpladocs.com/about* — last reviewed 2026-05-04 # Our Mission > SimplaDocs exists to bridge the gap between how teams work and how they could work — connecting people, platforms, and processes so that the impossible is a click away. ## We believe every team deserves tools that work as hard as they do. --- ## Who We Are SimplaDocs is a bridge. We connect teams together in platforms that work as a source of truth. We connect different platforms and services, orchestrating processes that ease people's lives. We are an AI-native operational transformation consultancy. We consult AND we build — embedding ourselves in operations to identify bottlenecks, structure the context AI needs to succeed, train teams to adopt new workflows, and deploy the agents and tools that make change real. --- ## What We Do We bridge the gap — leading teams to a place where people work smarter and faster, to deliver better results. We organize all existing paths, create new ones, and build a place where the impossible is a click away. --- ## What Drives Us ### Connected Everything we build is about linking people, platforms, and processes. ### Bright & Vivid We bring light, intensity, and joy to our work. ### Precise yet Dynamic Geometric discipline with a sense of movement. ### Approachable Making the complex feel simple. --- ## Our Positioning SimplaDocs is tool-agnostic by default, with deepest specialty in the Coda ecosystem (rebranding as Superhuman Docs) and Superhuman Go agents. We are the #1 Expert Partner for both. Our durable capability isn't tied to a tool — it's our ability to transform how operations actually work. --- ## Ready to Work Together? Let us show you how SimplaDocs can transform your operations. **CTA:** [Let's Talk](/contact) --- ## Topic Owners - **Scott Collier-Weir** — Coda / Superhuman Docs / Superhuman Go specialist, Founder - **Steven Hurtado Roldan** — AI strategy, methodology, measurement ## Related - [About SimplaDocs](https://simpladocs.com/about) - [Our Process](https://simpladocs.com/our-process) - [Our Team](https://simpladocs.com/team) - [Contact Us](https://simpladocs.com/contact) --- *Source: https://simpladocs.com/our-mission* — last reviewed 2026-05-04 # Our Process > SimplaDocs follows a proven four-step delivery process — Discovery, Fit Assessment, Build, and Integrations & Rollout — grounded in the Value Chain methodology (Assess → Structure → Enable → Deploy) to ensure every engagement delivers solutions that truly work. ## A proven approach from discovery to deployment — designed to deliver solutions that truly work. Our process is not a black box. It is collaborative, transparent, and designed to make sure the solution we build is one your team can own and maintain long after we're done. --- ## The Value Chain: Our Overarching Methodology Before diving into project steps, every engagement is scoped through our four-stage Value Chain: - **Assess** — Map workflows, diagnose readiness, surface what's blocking AI adoption - **Structure** — Organize the content, knowledge, and guardrails AI needs to succeed - **Enable** — Train teams and onboard AI tools alongside them — adoption before deployment - **Deploy** — Build and maintain the agents and tools that make change real, with measurable ROI --- ## Project Delivery Steps ### 01 — Discovery We start by understanding your team, workflows, and goals. We dig deep into how your organization operates so we can identify the highest-impact opportunities. **What happens:** - Stakeholder interviews - Workflow mapping - Pain point identification - Goal alignment *Maps to Value Chain: Assess* --- ### 02 — Fit Assessment Not every problem needs Coda. We honestly evaluate whether our approach is the right fit for your needs, and recommend the best path forward. **What happens:** - Technical feasibility analysis - Tool evaluation - Scope definition - Timeline planning *Maps to Value Chain: Assess → Structure* --- ### 03 — Build We build collaboratively — not in a black box. Your team stays involved throughout the development process, with regular check-ins and demos. **What happens:** - Iterative development - Regular demos - Feedback loops - Quality assurance *Maps to Value Chain: Structure → Deploy* --- ### 04 — Integrations & Rollout We connect your solution to the tools you already use, train your team, and ensure a smooth rollout with ongoing support. **What happens:** - Third-party integrations - Team training - Documentation - Ongoing support *Maps to Value Chain: Enable → Deploy* --- ## Why Our Process Works - **No black boxes.** You see the work as it happens. - **Fit before build.** We won't build something that doesn't fit your needs. - **Adoption first.** We train teams before full deployment — not as an afterthought. - **Flexible engagement models.** One-off projects, full-scale overhauls, ongoing retainers. --- ## Ready to Start? Let's kick off with a discovery call and see how we can help. **CTA:** [Schedule a Call](/contact) --- ## Topic Owners - **Scott Collier-Weir** — Coda / Superhuman Docs / Superhuman Go specialist, technical delivery - **Steven Hurtado Roldan** — AI strategy, methodology design, measurement - **Jordyn Goffo** — Project management, operations improvement, consulting delivery ## Related - [Our Services](https://simpladocs.com/services) - [Our Work / Case Studies](https://simpladocs.com/work) - [About SimplaDocs](https://simpladocs.com/about) - [Contact Us](https://simpladocs.com/contact) --- *Source: https://simpladocs.com/our-process* — last reviewed 2026-05-04 # Our Team > The SimplaDocs team is a group of passionate operational transformation experts — Coda specialists, AI strategists, and project managers — dedicated to making businesses work smarter through the Assess → Structure → Enable → Deploy methodology. ## Meet the people behind SimplaDocs — passionate experts who live and breathe operational excellence. --- ## Leadership & Core Team ### Scott Collier-Weir — Founder & Lead Consultant Known as "The Coda Guy," Scott is a recognized leader in the Coda community with thousands of YouTube followers learning from his tutorials. He founded SimplaDocs in 2020 to bridge the gap between powerful no-code platforms and the operational challenges businesses face every day. Under his leadership, SimplaDocs has grown to serve 200+ companies including Spotify, Netflix, and Fidelity. **Specialties:** Coda, Superhuman Docs, Superhuman Go, AI Agents, platform architecture --- ### Steven Hurtado Roldan — Director of Business Strategy & AI Steven leads SimplaDocs' AI practice and business strategy. A systems thinker and polymath, he translates complex problems into simple, working solutions. He heads the "AI No Jargon" initiative, making AI adoption practical and accessible for businesses. **Specialties:** AI strategy, business strategy, AI No Jargon, methodology, measurement --- ### Jordyn Goffo — Project Manager & Operations Lead Jordyn coordinates complex client engagements and drives operational improvements. She is growing into the COO function, bringing rigor and clarity to every project delivery. **Specialties:** Project management, operations improvement, consulting delivery, partnerships --- ### Rachel — Head of Sales Rachel leads sales and revenue operations at SimplaDocs, with a focus on AI-improved sales processes and content distribution. **Specialties:** AI-improved sales, sales operations, content distribution --- ### Daniel Velho — Senior Consultant Daniel is SimplaDocs' second hire, bringing deep Coda expertise and a client-first approach to every project. He leads complex enterprise engagements and is growing into a people leadership role within the team. **Specialties:** People ops, product management, enterprise Coda delivery --- ## What We Stand For - **Build, Don't Slide** — Every engagement delivers working systems, not decks. - **Clarity Over Cleverness** — Solutions your team can understand, own, and evolve. - **Discovery First** — We invest time understanding how you work before building anything. - **Partnership, Not Projects** — We think long-term, toward self-sustaining operations. --- ## Want to Join Us? We are always looking for talented people who share our passion for operational excellence. **CTA:** [View Open Positions](/careers) --- ## Topic Owners - **Scott Collier-Weir** — Coda / Superhuman Docs / Superhuman Go specialist - **Steven Hurtado Roldan** — AI strategy & business strategy - **Jordyn Goffo** — Project management, operations improvement, consulting, partnerships - **Rachel** — AI-improved sales, sales operations, content distribution - **Daniel Velho** — People ops, product management ## Related - [About SimplaDocs](https://simpladocs.com/about) - [Our Mission](https://simpladocs.com/our-mission) - [Careers](https://simpladocs.com/careers) --- *Source: https://simpladocs.com/team* — last reviewed 2026-05-04 # Join Our Team > SimplaDocs is a growing AI-native operational transformation consultancy looking for curious problem-solvers who want to build systems that transform how businesses operate. ## We're building a workplace where curiosity drives progress, and every voice matters. We challenge ideas with respect, trust our people to lead with integrity, and believe work-life balance isn't optional — it's essential. --- ## Who We're Looking For Self-starters who love problem-solving and seek out new challenges. If you're excited about Coda, Superhuman, and AI operations and want to build custom solutions that transform how businesses operate, we want to hear from you. **Traits we value:** - You love solving complex problems - You communicate clearly and often - You care about quality over speed - You are curious and always learning --- ## Coda Developers We're always looking for talented Coda developers to join our growing team. Send your resume to [info@simpladocs.com](mailto:info@simpladocs.com) and submit your Coda assessment doc for consideration. --- ## New to Coda? No Problem. Our team thrives on diverse skill sets and perspectives. If you're passionate about operations, automation, and helping businesses scale — reach out. We'd love to talk. --- ## Open Positions We post active openings on this page as they become available. When no listings appear, we are always interested in hearing from great people. **Don't see the right role?** Send us your resume and tell us how you could contribute. → [Email Us](mailto:info@simpladocs.com?subject=General%20Application) --- ## Related - [Meet Our Team](https://simpladocs.com/team) - [About SimplaDocs](https://simpladocs.com/about) - [Contact Us](https://simpladocs.com/contact) --- *Source: https://simpladocs.com/careers* — last reviewed 2026-05-04 # Let's Talk > SimplaDocs responds to all inquiries within 24 hours — reach out to discuss your operational challenges and how our AI-native transformation consultancy can help. ## Ready to transform your operations? We'd love to hear from you. --- ## Get in Touch Fill out the contact form and we will get back to you within 24 hours. **What to tell us:** - Your name and company - Your email and phone number - What you're trying to solve or build After submitting, you can optionally book a call directly on our calendar. --- ## Contact Information - **Email:** [info@simpladocs.com](mailto:info@simpladocs.com) - **Response time:** We typically respond within 24 hours. --- ## What Happens After You Reach Out 1. We review your message and context 2. A SimplaDocs team member responds within 24 hours 3. We schedule a discovery call to understand your workflows, goals, and pain points 4. We scope a solution and present the right fit --- ## Have Questions First? Check out our services page to learn more about what we offer, or explore our case studies to see real results. - [View Services](/services) - [See Our Work](/work) --- ## Related - [Our Services](https://simpladocs.com/services) - [Our Work](https://simpladocs.com/work) - [About SimplaDocs](https://simpladocs.com/about) --- *Source: https://simpladocs.com/contact* — last reviewed 2026-05-04 # The #1 Coda Expert Partner Consultancy > SimplaDocs is the leading Coda consultancy — the #1 Coda Expert Partner and #1 Superhuman implementation partner — having served 200+ companies including Spotify, Netflix, Fidelity, MrBeast, Qualtrics, and DoorDash, with 215+ projects completed, 110+ Coda Packs built, and 83,000+ hours saved for clients. ## SimplaDocs has built custom Coda solutions for 200+ companies. We are the largest Coda Pack builder with 110+ Packs designed and actively maintained. Official Coda Expert Partner — the highest tier in Coda's partner program. --- ## What Is a Coda Consultant? A Coda consultant is a specialist who designs, builds, and optimizes custom business solutions on the **Coda platform**. Unlike generic no-code consultants, a Coda consultant has deep expertise in Coda's unique document-database hybrid model, Packs ecosystem, and automation capabilities. Coda consultants help organizations replace scattered spreadsheets, disconnected tools, and manual processes with unified, automated workspaces that scale. The best Coda consultants have official **Coda Expert Partner** status, custom Pack development experience, and a proven track record across enterprise clients. SimplaDocs is the leading Coda consultancy. Founded by **Scott Collier-Weir (The Coda Guy)**, a recognized community leader with thousands of YouTube followers, we have completed 215+ projects across 170+ use cases and saved clients over 83,000 hours of manual work. --- ## Key Stats - **200+** Companies Served - **215+** Projects Delivered - **110+** Coda Packs Built - **83k+** Hours Saved --- ## Why SimplaDocs Is the Top Coda Consultancy ### #1 Coda Expert Partner Official Coda Expert Partner working directly with Coda on platform features and capabilities. The leading Coda and Superhuman implementation partner. ### Founded by The Coda Guy Scott Collier-Weir is a recognized leader in the Coda community, known as "The Coda Guy," with thousands of followers learning from his YouTube tutorials and educational content. ### Largest Coda Pack Builder We have designed and actively maintain 110+ Coda Packs — more than any other consultancy. Over 15 of our Packs are included in Coda's official enterprise bundle. ### 200+ Companies Served From 5-person startups to Fortune 500 enterprises including Spotify, Netflix, Fidelity, MrBeast, Qualtrics, and DoorDash. ### 83,000+ Hours Saved Our custom solutions deliver measurable ROI. 91% of clients recommend SimplaDocs, and our CIO clients call us "the best ROI I've ever made." --- ## Trusted by Industry Leaders Spotify · Netflix · Fidelity · MrBeast · Qualtrics · DoorDash · A Global Management Consultancy · A U.S. State Environmental Agency · A Leading Engineering Consultancy · Nowadays Media · Bipty SimplaDocs has built custom Coda solutions for leading organizations across technology, finance, media, government, and entertainment. --- ## The Largest Coda Pack Builder SimplaDocs has designed and actively maintains over 110 Coda Packs, making us the biggest Pack builder in the Coda ecosystem. More than 15 of our Packs are included by Coda in their official enterprise bundle. **Packs in Coda's Official Enterprise Bundle:** Coda Doc Explorer · Monday.com · Harvest · Documint · Smartsheet · Gmail · Slack · Google Chat · Databricks · Xano · Lemon Squeezy · Pabbly · Klaviyo · Mailgun · Twilio · Jotform · Paperform · Strava · and more --- ## What a Coda Consultant from SimplaDocs Can Do for You ### Expert Consultants Seasoned Coda developers who architect and build custom solutions tailored to your business workflows. ### AI Context Engineering AI-powered operational automation and context-aware solutions built natively on Coda. ### Coda Packs Custom integrations connecting Coda with your existing tools. 110+ Packs built, 15+ included in Coda's official enterprise bundle. ### Coda Admin as a Service Ongoing workspace management, maintenance, and optimization handled by our expert team. ### Workspace Health Report Thorough audits of your Coda workspace covering performance, structure, and security. ### Coda School Self-paced Coda training with 1:1 expert support and a learning community for your team. ### Doc Review Low-commitment review of your existing Coda docs with actionable improvement recommendations. ### Templates Pre-built, customizable Coda templates designed for common business workflows and use cases. [View All Services →](/services) --- ## What to Look for in a Coda Consultant When evaluating Coda consultants and implementation partners, these criteria matter most: - Official Coda Expert Partner status - Proven track record with enterprise clients (Spotify, Netflix, Fidelity) - Custom Coda Pack development capability (110+ Packs built) - AI and automation expertise - Packs included in Coda's official enterprise bundle - Flexible engagement models (one-off, retainer, fractional CTO) - Founder-led with deep community credibility --- ## Results from Our Coda Consulting Projects ### U.S. State Environmental Agency — Government **Challenge:** Manual, slow workflows across multiple departments causing bottlenecks and data silos. **Solution:** Built a scalable Coda system with automated workflows, cross-department visibility, and real-time reporting. **Result:** 11x faster workflows, 250+ hours saved. Their CIO called SimplaDocs "the best ROI I've ever made." [View case study →](/work/state-environmental-agency) ### Nowadays Media — Media & Advertising **Challenge:** Campaign management required 3+ people to coordinate manually across scattered tools. **Solution:** Custom Coda workspace with automation Pack connecting their ad platforms, budgets, and reporting. **Result:** 1 person now does the job of 3. "Easily the best money we are spending every month." [View case study →](/work/nowadays-media) ### Global Management Consultancy — Management Consulting **Challenge:** Budget tracking across 20+ teams relied on disconnected spreadsheets with no single source of truth. **Solution:** Unified budgeting system in Coda with real-time dashboards, automated roll-ups, and team-level access controls. **Result:** Single source of truth for 20+ teams, eliminating manual consolidation. [View case study →](/work/global-management-consultancy) [See All Case Studies →](/work) --- ## Frequently Asked Questions About Coda Consulting **What is a Coda consultant?** A Coda consultant is a specialist who designs, builds, and optimizes custom business solutions on the Coda platform. Coda consultants help organizations replace scattered spreadsheets and disconnected tools with unified, automated workspaces. SimplaDocs is the #1 Coda Expert Partner consultancy, with 215+ projects delivered for companies including Spotify, Netflix, and Fidelity. **How much does a Coda consultant cost?** Coda consulting rates vary by scope and complexity. SimplaDocs offers flexible engagement models including one-off projects, full-scale operational overhauls, and ongoing monthly retainers. We start every engagement with a discovery call to understand your needs and right-size the solution. **How long does a Coda consulting project take?** Most Coda consulting projects are delivered in 2-6 weeks depending on complexity. Simple automations can be live in days, while full operational systems take a few weeks to design, build, and roll out. We pair discovery with rapid prototyping to iterate quickly. **What is the difference between a Coda consultant and doing it myself?** While Coda is user-friendly, a Coda consultant brings deep platform expertise, custom Pack development capabilities, and experience across 170+ use cases. SimplaDocs has built 110+ Coda Packs — more than any other consultancy — and 15+ are included in Coda's official enterprise bundle. A consultant delivers production-grade solutions faster, with fewer iterations, and ensures your system scales as your team grows. **Can a Coda consultant integrate with our existing tools?** Yes. Coda integrates with Slack, Google Workspace, Jira, Salesforce, and hundreds of other tools. SimplaDocs specializes in building custom Coda Packs — we have designed and maintain 110+ Packs including integrations with Monday.com, Harvest, Smartsheet, Databricks, Gmail, Twilio, Klaviyo, and more. **What industries do Coda consultants work with?** SimplaDocs has served 200+ companies across technology, finance, government, media, entertainment, and professional services. Our clients range from 5-person startups to Fortune 500 enterprises including Spotify, Netflix, Fidelity, DoorDash, and Qualtrics. **Who built the most Coda Packs?** SimplaDocs is the largest and most prolific Coda Pack builder, with over 110 Packs designed and actively maintained. More than 15 of our Packs are included in Coda's official enterprise bundle, including Coda Doc Explorer, Monday.com, Harvest, Documint, Smartsheet, Gmail, Slack, Google Chat, Databricks, Xano, Lemon Squeezy, Pabbly, Klaviyo, Mailgun, Twilio, Jotform, Paperform, and Strava. --- ## Ready to Work with the #1 Coda Consultancy? Tell us what you need — we'll show you what's possible. **CTA:** [Let's Talk](/contact) --- ## Topic Owners - **Scott Collier-Weir** — Coda / Superhuman Docs / Superhuman Go specialist, Coda Packs, platform expertise - **Steven Hurtado Roldan** — AI strategy, AI Context Engineering, methodology - **Jordyn Goffo** — Consulting delivery, project management, partnerships - **Daniel Velho** — Coda expertise, enterprise delivery, Admin as a Service ## Related - [Our Services](https://simpladocs.com/services) - [Our Work / Case Studies](https://simpladocs.com/work) - [About SimplaDocs](https://simpladocs.com/about) - [Contact Us](https://simpladocs.com/contact) --- *Source: https://simpladocs.com/coda-consultants* — last reviewed 2026-05-04 # SPB Utility Services > How a 15-person utility operator replaced enterprise maintenance software with a custom operating system built on Coda. **Replaced $12K/year of enterprise tools** Outgrown the cheap tools, priced out of the enterprise ones — so they built the one in between. Client: SPB Utility Services Industry: Utilities Services: Custom App, Automation ## Key metrics - $12K/year — Enterprise tool cost removed - 2 weeks — Build to live on operator iPads - 70 — Sites on one system ## What we built Replaced $12K/year of enterprise maintenance licences with a Coda work-order app the field team runs from iPads across roughly 70 sites. ## Challenge Daniel Peterson, founder of SPB Utility Services, faced a predicament most growing businesses know well: he’d outgrown his tools, but hadn’t yet scaled into the enterprise ones built to replace them. SPB manages water and wastewater utilities across roughly 70 locations in northern Nevada with a team of about 15 people. Field operators were spending too much time on lengthy, open-ended work orders that were difficult to navigate and easy to abandon mid-fill. Without native filtering, operators had to sift through hundreds of open work orders across all sites just to find their assignments — causing jobs to slip and time wasted on rework. Backlogs grew and incomplete entries became the norm. For Daniel, keeping up meant hours of manual, tedious editing each week, touching work orders one by one. “The tools we were using previously were great products but they weren’t worth the money,” said Daniel. “At our size, we didn’t use most of the functionality that they offered, so it was either overpay to over-engineer, go back to more rigid project management tools, or build something myself. I chose the latter.” He came to SimplaDocs with a clear goal: build an application that could support SPB’s operations today and grow with the business tomorrow. ## Solution After hearing Daniel’s vision and understanding SPB’s current state, SimplaDocs created a two-phase process. First: get the work order system under control. Second: build a leadership operating system bespoke to SPB’s way of working that would support its growth. Phase one started by mapping the user journey for the field operations team. Through user interviews with SPB team members, SimplaDocs understood what wasn’t working and developed a plan to streamline the process — adding easy-to-set recurring tasks and intuitive filtering that saved operators time placing work orders and gave them full transparency into their day’s assignments. Within two weeks of developing the app, SimplaDocs had completed onboarding and launched SPB’s new system to all field operators’ iPads. Next, the team built the tools Daniel needed to manage his business strategically. Bulk editing work orders — previously hours of tedious manual updating each week — was replaced by a web of automations that let him update hundreds of work orders across all of northern Nevada in minutes. One of the most impactful moments came when Daniel used AI to mock up his ideal dashboard. “I spent at least 10 hours one weekend creating the perfect dashboard for our new work order management system,” he said. After walking the team through how he wanted to engage with it, they brought it to life in Coda — fully functional and connected to his live data. - Bespoke web app for field operations, launched to operators’ iPads within two weeks - Work order system with recurring tasks, intuitive filtering, and essential-fields-only workflows - Automated bulk editing replacing hours of weekly manual updates - Leadership dashboard, built from Daniel’s own AI mockup, monitoring work orders and blockers statewide ## Results - Replaced $12K/year in enterprise tools with a custom-built Coda app SPB uses every day - Launched to field operators across roughly 70 locations within two weeks of development - Bulk work order updates across northern Nevada went from hours of manual editing each week to minutes - Eliminated backlog clutter through simplified, essential-fields-only workflows ## How the engagement ran ### How long did it take? Two weeks from build to launch on field operators’ iPads for phase one. The operating-system build-out is ongoing. The engagement ran in 2026. ### What did the engagement look like? Two phases: a defined build to get the work order system under control, then an ongoing operating-system build-out working directly with the founder. ### Which systems did it touch? Coda, iPad, UpKeep, MaintainX ## Impact Field operators save time each week filing and finding work orders, and Daniel manages operations behind the scenes with automations handling the repetitive work and a dashboard giving him line of sight into the health of his business. ## Where it is now SPB is continuing the momentum by building out a full custom operating system. They’re adding an asset management database that lets field operators quickly find digital documentation of parts and processes — finally replacing paper manuals — as well as an internal wiki mapping SPB’s standard operating procedures, helping new hires onboard faster and the broader team stay aligned. > The most important thing SimplaDocs delivered was peace of mind. Now I know I have the freedom to build what’s best for my operations, my people, and my business — without being constrained by tools or ongoing costs. > — Daniel Peterson, Founder, SPB Utility Services > From the start, I was struck by how thoughtful the SimplaDocs team was. They didn’t just implement what I asked — they challenged my thinking and thought strategically about what they were building. SimplaDocs felt more like thought partners than a consultant. > — Daniel Peterson, Founder, SPB Utility Services --- Source: https://simpladocs.com/work/spb-utility-services # Ganden > How SimplaDocs rescued a 70-person engineering firm’s Coda system and became their long-term partner. **Cut entry time by 73%** A 170MB production document, 65 daily users, and no room left to grow — optimised in place, with no migration and no rebuild. Client: Ganden Industry: Engineering & Infrastructure Consulting Services: Doc Audit, Automation ## Key metrics - 11s → 3s — Timesheet entry, 65 daily users - 2 min → 6s — New project creation - 69,000+ — Rows under automated archiving ## What we built Audited a 170MB production Coda doc, moved 133 real-time metric columns to hourly automations, and built Google Sheets archiving for 69,000 rows — while 65 people kept working in it. ## Challenge Ganden is a Gold Coast-based engineering consultancy specialising in water infrastructure design, with over 1,000 completed projects and nearly 70 staff across seven offices throughout Australia. For over five years, two of its operational leaders, working without any outside development support, had built the entire backbone of the business inside a single Coda document: timesheets, project tracking, bids, financials, invoicing, and task management. The system was a genuine achievement. It had grown to over 170 MB, supporting a master table with 5,000+ rows across 315 columns and 133 real-time metric columns running calculations across the entire dataset. More than 50,000 timesheet rows had accumulated over the years, managed through a manual archiving process into a separate document. And 65 people depended on it every day. That lack of speed was costing the team daily. Every timesheet entry took roughly 11 seconds. Creating a new project could take nearly two minutes. With 20 to 30 people working simultaneously, one person’s entry slowed everyone else down. ## Solution SimplaDocs started with a comprehensive doc audit to identify exactly where the performance drag was coming from. The root cause was clear: over a hundred metric columns were recalculating on every single timesheet entry, cascading computation across every concurrent user. On top of that, default filter settings were forcing full recalculations every time a new project was created. The performance fixes were surgical and immediate. Critical roll-up columns were converted to scheduled automations that refreshed hourly instead of recalculating in real time, and filter defaults were reset to eliminate unnecessary computation. None of this required changing how the team worked day to day. With the immediate pain resolved, SimplaDocs turned to the deeper structural problem: tens of thousands of timesheet rows with no automated management. They designed and built a complete archiving and restoration system spanning Google Sheets and Coda, connected by automated scripts. Historical data syncs continuously, projects flagged as active stay live, and archived data can be pulled back when needed — because in engineering consulting, closed projects sometimes reopen months later. The archiving system passed its ultimate test during invoicing week, when 20+ project managers reviewed all active project finances simultaneously. The entire cycle ran without a single issue. - Doc audit isolating the recalculation cascade across 133 metric columns - Roll-up columns converted to hourly scheduled automations - Archiving and restoration system spanning Google Sheets and Coda - Xero integration replacing a manual export-and-paste process - Employee performance reporting across all 70 staff, ready for annual reviews - Rate card changes propagated correctly through archived data ## Results - Timesheet entry dropped from roughly 11 seconds to 3 seconds across 65 daily users and 1,500 entries per month - New bids and projects went from nearly two minutes to under six seconds - Automated archiving and restoration replaced a manual copy-paste process across 69,000+ rows - Xero integration removed a manual export-and-paste consuming hours of the Managing Director’s week - A six-week audit expanded into a 15 hr/week retainer with no end date ## How the engagement ran ### How long did it take? A six-week doc audit that expanded into an ongoing retainer at 15 hours a week, with no end date. ### What did the engagement look like? A fixed-scope performance audit first, then an open-ended retainer at 15 hours a week run through weekly syncs. Nick restructured Ganden’s own internal meetings to keep those syncs focused purely on implementation. ### Which systems did it touch? Coda, Google Sheets, Xero ## Impact SimplaDocs optimised the live production document while 65 people continued using it every day. No migration. No rebuild. No disruption. Measurable results arrived within weeks, and every improvement was validated by actual user feedback before being rolled out. ## Where it is now With the core infrastructure in place, the scope expanded to other operational drag. Bid and sales dashboards, automated timesheet reminders, and resource planning tools joined the roadmap, and an employee performance reporting system was built to generate individual and team reports across all 70 staff in time for annual reviews. “We’re definitely keen to keep this engagement going for the foreseeable,” Nick said. “We’ve just started.” > What you’ve done so far is fantastic. Everything you’re doing, we’re sort of seeing immediate improvements and results. > — Nick Steer, Operations Manager, Ganden > What you’re doing is amazing and it’s well beyond our capabilities. > — Nick Steer, Operations Manager, Ganden > The two things we see over and over again are complexity and speed. > — Darron Nutt, Managing Director, Ganden --- Source: https://simpladocs.com/work/ganden # Campaign Automation > How Nowadays Media went from manual processes to one person doing the job of three with SimplaDocs automation. **1 person doing the job of 3** How Nowadays Media scaled their influencer campaigns with automation. Client: Nowadays Media Industry: Digital Marketing / Influencer Campaign Management Services: Automation, Custom Pack ## Key metrics - 4 min → seconds — Time per campaign email ## What we built Replaced manual outreach across thousands of influencers with automated email sends, response tracking, contract generation, and one hub for reporting. ## Challenge Nowadays Media faced significant operational bottlenecks managing large-scale influencer campaigns. They needed to contact thousands of people and track thousands of posts per campaign while maintaining manual processes that were time-consuming and inefficient. ## Solution SimplaDocs created a custom Coda automation system that streamlined the entire campaign management workflow, from outreach to reporting. - Automated email outreach capabilities - Automatic email response tracking - Contract generation functionality - Influencer-specific data and metrics reporting - Integrated communications, financials, scheduling, and data management hub ## Results - Email campaigns that previously required 4 minutes per email now send in seconds - Increased influencer outreach capacity per campaign, enabling business growth - Consolidated operational visibility across all business functions - One person can now accomplish the work of three employees ## Impact Nowadays Media transformed their operations from manual, time-intensive processes to streamlined automation. The investment in SimplaDocs became their best monthly spend, with weeks of work simplified into a single click. > This is easily the best money we are spending every month... SimplaDocs has helped simplify weeks of work into one simple click of a button... It's one person doing the job of at least three after the automations. > — Kaspar Povilanskas, Co-Founder, Nowadays Media --- Source: https://simpladocs.com/work/nowadays-media # Fractional CTO > How Bipty transformed their business with SimplaDocs as their fractional CTO partner. **Best investment of 2023** How Bipty transformed their business with a fractional CTO partnership. Client: Bipty Industry: Fashion / Clothing Lending Startup Services: Fractional CTO, Pack Creation ## What we built Fractional CTO — a dedicated builder embedded in their channels and daily workflows, not an external vendor. ## Challenge Bipty needed to build infrastructure by integrating a technical partner who could understand their operations, identify process improvements, and function as an extension of their internal team. ## Solution SimplaDocs provided fractional CTO services, with a dedicated builder who conducted deep discovery across team roles and daily workflows. They immersed themselves in company communication channels, developed solutions aligned with business vision and customer needs, and became an integrated team member rather than an external vendor. - Deep discovery across team roles and daily workflows - Full immersion in company communication channels - Solutions aligned with business vision and customer needs - Integrated team member approach rather than external vendor ## Results - Described as "transforming our business" - Rapid development velocity achieved - Full transparency and visibility into processes - Observable daily progress and forward momentum ## Impact Bipty saw strong ROI from their partnership with SimplaDocs, describing it as "by far the best investment of 2023." The holistic approach to solving tech problems set SimplaDocs apart from any other dev company they had worked with. > It was a big investment for our startup, but by far the best investment of 2023! What I love most about SimplaDocs, that I have yet to see with any other dev company, is how they take a holistic approach to solving your tech problems. > — Natalia Ohanesian, Founder, Bipty --- Source: https://simpladocs.com/work/bipty # Scalable Systems for a State Agency > How a U.S. state environmental agency built a scalable future with SimplaDocs, achieving 11x faster workflows. **11x faster workflows** How a U.S. State Environmental Agency Built a Scalable Future with SimplaDocs. Client: U.S. State Environmental Agency Industry: Government / Environmental Regulation Services: Process Automation, Forms ## Key metrics - 6 hrs → ~1 hr — Application review time - 250+ — Hours saved in months ## What we built Rebuilt a permit application log that ran through a dozen stakeholders as digital forms, triage notifications, role-specific views, and supervisor dashboards. ## Challenge When the CIO of a U.S. state environmental agency first discovered Coda, he immediately saw its potential. He built tools that replaced spreadsheets, streamlined tasks, and gave his team new ways to work. His early solutions quickly proved their value — and other bureaus began to take notice. But with growing interest came a new challenge: how to make these tools perform at scale, work seamlessly for multiple teams, and be easily maintained over time. He knew the vision was bigger than one person could deliver alone. That's when he turned to SimplaDocs. ## Solution From the beginning, it was clear that what the agency gained in SimplaDocs was more than a contractor; they brought in a savvy thought partner. Rather than simply refining individual documents, SimplaDocs helped them take a step back and think in systems — shifting from single-purpose tools to an interconnected, modular ecosystem that could evolve with the department's needs. SimplaDocs was tasked with tackling an application log for environmental permits — a manual process that involved a dozen internal stakeholders and a suboptimal experience for applicants. Together, they reimagined the experience at every touchpoint, eliminating key sources of human error and bottlenecks. - Digital forms replacing manual spreadsheet entry - Triage notifications automatically alerting team members of their next task - Role-specific views to avoid overwriting others' work - Real-time dashboards for supervisors - Applicant notifications for full transparency ## Results - Enabled the team to work 11 times faster than originally - Application review time dropped from six hours to just over an hour - Saved the team over 250 hours in several months - Rolled out dozens of interconnected systems across the department ## How the engagement ran ### Which systems did it touch? Coda, Spreadsheets ## Impact The agency continues to retain SimplaDocs because "they bring immense value to our agency." SimplaDocs also helped the department roll out dozens of smaller, interconnected systems — from emissions tracking tools to training workflows and internal reporting dashboards. The CIO's team serves as a hub for internal innovation. He's often approached by other bureaus asking, "Can Coda do this?" His answer is consistent: bring in SimplaDocs. > As a CIO, I've worked with many many vendors, and SimplaDocs was the best ROI I've ever made. > — CIO, U.S. State Environmental Agency > They're incredibly fast and they're incredibly good. From all of the vendors I've worked with, SimplaDocs brings me the highest ROI. They're worth every penny. > — CIO, U.S. State Environmental Agency --- Source: https://simpladocs.com/work/state-environmental-agency # Smarter Budgeting for a Global Consultancy > Building a smarter budgeting system for a global management consultancy, replacing spreadsheets with a collaborative platform. **One source of truth for 20+ teams** Building a Smarter Budgeting System for a Global Consultancy. Client: Global Management Consultancy Industry: Management Consulting Services: Budgeting, Dashboards ## Key metrics - 20+ — Product leads on one system - On demand — Leadership roll-ups and forecasts ## What we built Replaced Excel workbooks and email approvals with a submission workspace for 20+ leads, an admin workspace with automated roll-ups, and Slack notifications through the budget cycle. ## Challenge When a global management consultancy's Product & Platforms team set out to modernize their annual budgeting process, they were juggling over twenty products, dozens of stakeholders, and an overwhelming amount of spreadsheets. For the Finance & Planning team, managing this cycle meant long hours of manual consolidation, unclear ownership, and constant rounds of email and Slack messages just to confirm what was approved and what wasn't. The budgeting process had grown increasingly complex. Each of the twenty product leaders managed their own budgets, while the F&P team manually consolidated everything into large Excel workbooks. Updates were submitted over email, revisions tracked in comment threads, and key data — like rate cards, hiring plans, and vendor spend — were constantly at risk of becoming outdated. ## Solution SimplaDocs partnered with the consultancy to design and deliver a collaborative budgeting and forecasting platform built on Coda, tailored specifically to the firm's needs. The solution centered around two connected spaces: a submission workspace for the 20 product and platform leads to enter and track their labor and non-labor budget requests, and an administrative workspace for the Finance & Planning team to review, approve, and report on submissions with automated roll-ups and forecasting dashboards. Throughout the budgeting cycle, automated Slack notifications kept communication flowing — alerting users when requests were submitted, reviewed, or returned for updates. Dashboards gave leadership real-time visibility into budget allocations, trends, and forecasting scenarios. - Submission workspace for 20+ product leads - Administrative workspace with automated roll-ups and forecasting - Automated Slack notifications for budget cycle communication - Structured data exports aligned with SAP and financial workflows ## Results - Reduced manual coordination and rework across email and Slack - Given leadership on-demand visibility into roll-ups, forecasts, and key trends - Streamlined approvals and eliminated version confusion between departments - Enabled faster decision-making cycles ## Impact Today, the budgeting process is faster, clearer, and more collaborative. Product leaders can submit and track requests with confidence, while the finance team can focus on analysis rather than administration. What began as a spreadsheet replacement became something bigger — a shared space that aligned finance, product, and leadership on a single source of truth. > It's not just about the tool. It's about how much smoother the entire process feels. We finally have time to focus on strategy, not spreadsheets. > — Finance & Planning Lead, Global Consultancy > Instead of chasing updates, we were reviewing decisions. The conversation shifted from "What's the latest file?" to "What does this data tell us?" > — Finance & Planning Lead, Global Consultancy --- Source: https://simpladocs.com/work/global-management-consultancy # Operational Excellence for an Engineering Consultancy > How a leading engineering consultancy achieved operational excellence with SimplaDocs, eliminating manual work and enabling scalable project management. **No backfill needed after their PM retired** How a leading engineering consultancy achieved operational excellence with SimplaDocs. Client: Leading Engineering Consultancy Industry: Building Services Engineering Services: Automation, Coda Pack ## Key metrics - Hours → minutes — Task creation time ## What we built Replaced manual ticket re-entry between Synergy and Coda with a bespoke Pack that syncs both systems and generates tasks automatically. ## Challenge A leading building services engineering consultancy was managing thousands of projects annually across mechanical, electrical, hydraulics, fire protection, and vertical transportation services. They had hired two different freelance contractors to create an operations infrastructure, but neither implementation could scale to meet the needs of an enterprise company with employees across multiple offices. Their project management process had become a frustrating cycle of repetitive manual work. The team had implemented a project management tool for architecture and construction, but the tool's rigidity didn't align with how they actually worked. Project managers were manually recreating tickets into Coda, then porting information back and forth between the two systems. ## Solution SimplaDocs began by thoroughly assessing what had been tried before and why it failed. Rather than jumping straight to building, they worked collaboratively with the client through weekly check-ins and daily async communication. SimplaDocs identified two critical bottlenecks: manual data translation between systems, and hours spent on routine task creation. They built a bespoke Coda Pack that automated the connection between the existing PM tool and Coda, eliminating the time-consuming double-entry problem. They also added intelligent business logic to automate task generation, transforming hours of manual work into a simple form. SimplaDocs also trained the team on how to maintain and optimize the new system, ensuring long-term success beyond the initial implementation. - Bespoke Coda Pack automating Synergy-to-Coda data sync - Intelligent task generation replacing hours of manual creation - Team training for long-term system ownership ## Results - Eliminated double-entry between Synergy and Coda with automated data sync - Reduced task creation time from hours to minutes through intelligent automation - Freed project managers to focus on strategic work rather than administrative tasks - Delivered enterprise-grade reliability that previous freelance builds couldn't match ## How the engagement ran ### Which systems did it touch? Synergy, Coda ## Impact When one of the firm's project managers retired, they didn't need to backfill the role. Another project manager could seamlessly take on those workstreams, while the firm redirected that headcount investment to more strategic areas like marketing. The success led the firm to expand their partnership with SimplaDocs to improve how it triages and approves its employees' billable hours. > SimplaDocs didn't just save us time, it changed how we think about our internal operations and investments. We were able to redirect effort and resources away from administration and toward more strategic areas of the business. > — Operations Director, Engineering Consultancy > The difference with SimplaDocs was immediately clear. Instead of relying on a single contractor, we had access to a team that brought structure, accountability, and deep expertise. > — Operations Director, Engineering Consultancy --- Source: https://simpladocs.com/work/engineering-consultancy # ChatGPT or Superhuman Go: pick where to build your agents > You want an AI agent and you're deciding between ChatGPT and Superhuman Go. Compare how each one handles setup, connectors, triggers and testing, using the same email triage agent built in both. **For:** Ops and team leads choosing where to build AI agents **Format:** pdf **Video:** https://youtu.be/byEnVY4RZkw ## What you'll be able to do - Pick a builder for a specific job, using a scorecard that compares ChatGPT and Superhuman Go on model, instructions, skills, context, tools, triggers, state and permissions. - Connect Gmail to an agent with read access only, so it can sort your inbox without being able to send or reply. - Set an agent to run on a schedule, on incoming email or while you type, and know which of those triggers each platform supports. ## What's inside - The seven capabilities every agent has: model, instructions, context, tools, triggers, state and permissions - What each capability is called in ChatGPT and in Superhuman Go, side by side - How each builder attaches reusable skills to an agent - How to connect your own systems when your app isn't in the connector directory, on both platforms - Superhuman Go's "While writing" trigger, with policy check and brand voice examples - The permission controls on each platform, from write approvals to admin controls - A scorecard of where ChatGPT leads and where Superhuman Go leads - Six common agent jobs, from customer reply guardrails to a research analyst, matched to the builder that fits ## Questions ### Which platform should I build my agent on? It depends on the job. Superhuman Go has more triggers, including email, Slack, doc events and a proactive trigger that runs while you type. ChatGPT agents run on a schedule or from Slack or its API. The PDF matches six common agent jobs to the builder that fits each one. ### Can an agent send emails without my approval? Only if you give it write access. Both platforms let you turn off write actions tool by tool, so an agent can read and search your inbox without being able to reply or send. ### Do I need to know how to code? No. Both platforms let you describe the agent in chat, then adjust its instructions, connectors and triggers in a manual editor. ## Transcript If you open your LinkedIn or Twitter these days, you're going to see hundreds of posts about AI agents. I'm going to show you today how to build agents yourself in two popular platforms, both ChatGPT and Superhuman Go. By the end of this video, you'll not only be equipped to build agents yourself, but you're also going to know the strengths of each platform and be able to pick what platform you're going to build agents on. As we look at building these agents, we're going to cover five core things. We're going to cover access, which is where to actually access and start building these agents in the platform. We're going to cover creating them, the experience of actually building them, either with AI or manually. We're going to talk about triggers, which is one of the most important things in agents, ensuring that these agents act when you want them to act. Connectors, which are the tools that you're going to give them access to, whether that be your email, calendar, communication tools or otherwise. And lastly, testing, to ensure that your agents work correctly. So come with me as we compare both platforms on these five. All right, so here we are. I'm inside of ChatGPT. Let's look at it first. You're going to see a lot of different things here on the side. I have agents down here because I pinned it. If you don't see your agents down here, look on the sidebar or look under more. But as I go to build an agent, I'm simply going to press this plus button. When I press plus in ChatGPT, I get shown this screen. I can build an agent with chat, so I can simply tell it, "I want an agent that does all my work for me." You can build it with chat, you can start from a template down here below, or you can start blank and configure it manually. That's quick. That's easy. That's how you access them, and those are the two different ways that we can actually build them. Let's look at Superhuman Go and see how theirs are built as well. When I'm in Superhuman Go, I am greeted with this screen. It says, "Here we go." On the left-hand side, I can see my tasks, and on the top, you're going to see agents. Agents really are the core aspect of Superhuman Go, so they're not going to be hidden under other menus. They're really going to be right in front of your face. I can create an agent with this plus button, and I'm going to be shown the manual setup right here. Or I can simply go to New Task and say, "I want to build a new agent that helps me with my email." All right. So those are the two different ways that you can actually access them and start building them. Let's go ahead and start building a real agent together so we can really experience these platforms. We're going to build a very simple agent today. It's going to be an email triage agent that, in the morning, before I wake up, is going to look at my email inbox and start sorting the noise that is so common in our emails from the things that we have to actually reply to. So let's start with ChatGPT and see what it does to develop this agent. You'll notice that ChatGPT is going to ask me different questions to clarify. I'm going to have it run every weekday at 5 a.m., because I really want to ensure that it's ready before I start. Personal must respond: I'm going to say, "You decide for me." The best thing about these is that this isn't final. ChatGPT is going to build your agent for you, and then you can go tweak it later with the manual settings. So let's go ahead and submit. All right. So now I'm inside of the manual builder, and you'll see that I have something set up for me already, but it's not quite done. First off is my instructions. I have a larger instruction base that gives it a role. It tells ChatGPT about me so it can better understand what might or might not be important. It tells it which emails to review and how to sort. Of course, this was developed by AI itself. Anything that AI does develop, please go in, read it yourself, tweak it, and make it more relevant to your own self. Now, aside from the instructions, there are some other important things we're going to look at. Those are our connections, where we're going to connect apps, skills, files, and memory. But before we jump into those, let's look at Superhuman Go and build the same agent. All right. So here we are with Superhuman Go. I want to give it the same prompt. I'm going to tell it that I want to build an email triage agent that helps me separate the noise in my inbox from personal emails and from people I really want to respond to. We're going to give it the exact same prompt and see what it does. Superhuman Go is doing a very similar experience. It's going to ask me clarifying questions. It's asking what email inbox I need to use. Great. Notice that I can tell it what to do as well. I want it every day at 5 a.m., because I want it really early. I'm going to submit that, and it's going to think through and build this agent for me. All right. So it's created it, and now, similar to ChatGPT, it's given me the option to open it. Oops, I don't want to run it. Let's go ahead and edit it. So here I am inside of the manual editing screen for Go. Now I can tweak everything myself. So we've just built an agent with each platform using AI, and once it's drafted by AI, we're going to start manually tweaking it. This next part is really important. It's about your connectors: how to connect your apps and tools in a secure way. They both handle it differently, but getting this part right ensures that your agents don't go rogue, expose information, or cause security vulnerabilities. So this is important to get right. Let's start with ChatGPT. We're going to add a connector. From here, I am going to browse apps, and apps give me a whole host of different apps that I can connect, custom MCPs, or I can search. I'm going to connect Gmail, because that is the email that I use. We're going to add it. Once it's added, there is this configure button. I really want to press this. I really want to see what's going on here and configure it correctly. You'll see that it gives me the option of an agent account or an end user account. I want it to search my inbox, so I'm going to give it my account. But I am going to go tool by tool and not give it certain actions. I really don't want it to accidentally go rogue and start responding to things or sending emails. So these are all my write actions. I'm going to uncheck them all, and it will not be allowed to do any of those pieces. These are my read actions. I can go line by line and give it less access if I want. For example, labels: I don't really need it to do labels. I don't need drafts. I might need profile. I might need attachments. But we can leave it with the rest of those. So now I'm going to go back, and you'll see that Gmail is connected. I could browse and connect different apps as well if I wanted to add my calendar. But that's how you generally add connectors to an agent in ChatGPT. Let's look at Superhuman Go. They've got a similar model and a similar permission style. When I'm inside of Superhuman Go, if I scroll all the way down, you're going to see I've got tools and access. By default, it has three toggles: web access, Superhuman Docs, and Gmail, Outlook and Calendar. Then there are also connections, where you can add and you can search. Again, hundreds of different connections. I can search Gmail, and there it is. It's already on for me because the agent already knew I needed it. Let's go in and see what it can and cannot do. You'll see here are all the write actions. Again, I don't need those, so I'm going to toggle them off so it cannot do those things. But can it read? Yes, it can. It can read thread counts, message counts, messages, and search messages. So we're going to always allow that, and we're going to allow that it can read. If you do use Superhuman Mail, the Superhuman product, you can just toggle this on, and that's all you need to do. That's literally it. All right. So those are our connectors inside of both agents. Again, connectors are what make agents powerful. They can work across and with your tools, but you need to ensure you configure them so you get the security aspects right. Next, we're going to talk about triggers, and this is probably one of the areas where these two platforms vary the most. So let's look at how they vary and how you can set them up for yourself. When I'm inside of my email triage agent here in ChatGPT, there's actually not a very clear trigger section. All that I see is in the top right, I have this automations section. When I press that, you'll see that I can do intervals, so it can run every hour, and or it can run daily on a schedule. You can pick the specific days that it runs and the time at which it runs. That's all we've got for triggers here. There actually are some hidden triggers. It's a little bit different. If we add a channel, there are two other ones we can use: Slack or an API. We can trigger it via API, or it can reply to messages in Slack. Now, this does get a bit more complex. This video is just showing you the basics of how to set up this agent. If you want a ton more technical information that lets you build advanced agents, you can look in the description below. I've got a large resource that dives really deep into each one of these agent builders and talks about every last thing you need to know. So go ahead in the description and grab that. We're not going to dive into that today, but know that you can also trigger these ChatGPT agents either with Slack messages or with the API. Let's go over and look at Superhuman Go and see their triggers. There are actually a lot more triggers, and it's very clear where they are. They're one of the blocks inside of your agent builder. Notice if I say add trigger, I actually have a whole section that's going to give me a ton of different triggers. I've been working with Superhuman Go since it was in beta, and this is constantly growing, so I know that there are only going to be more and more triggers that come. Here is their schedule, though. For example, I can do it daily, weekdays, weekly, or custom. I'm going to choose weekdays for right now, and I'm going to choose 5 a.m. in my time zone. But you'll notice here that they have so many other triggers you can use. First off, they've got a proactive trigger, which means that while you're typing, it's going to be watching what you type, and it may be able to trigger as you're typing based on certain keywords or things like that. This one's really powerful, and ChatGPT and Claude don't have this type of trigger. I've got email triggers as well, like every time an email is received or sent, or if you add a specific label. I've got Slack ones as well. And then I've got docs. If you use Superhuman Docs, there are a lot of doc-based triggers as well. So there are a lot more robust trigger options inside of Superhuman Go. But for this one, I want it to be a scheduled trigger, which I already have. So those are our triggers. Triggers simply tell an agent when it should run, and Superhuman Go is going to win in this area with its more robust triggers. All right. And lastly, testing. So now we've built our agent. We've got our prompt. We've got our triggers. We've got our names. Now we just have to test it to ensure that it works correctly. Inside of ChatGPT, we'll start here. I can press create, and once I press create, I'm going to be able to test it. The testing across these two platforms is very similar. You'll see I've got "Try in ChatGPT." I can try it. It's going to run by itself, but I can just say, "Run this agent." It's going to run the agent now and work through it. We'll come back to this in a moment. If we go back to Superhuman Go, it's very similar. You'll see Run agent. I can simply run this agent. We'll save it. When I run it, it goes to a chat screen, just like ChatGPT. It says, "I want to run this agent," and then the agent's going to start running, searching my inbox and looking for me. All right. So they've both been running for a while. You'll see that ChatGPT is running right now. It's still reading and checking. It's been about three to four minutes. Superhuman Go is done with its report. There we go. It's got priority and a lot more information on my email. I'm not going to scroll through it all because it is my personal email. But those are our two agent platforms. Again, there is far more to know about how these platforms work and how to build agents effectively. If you want a deeper comparison between the two, go into the description below to get that resource. If you've got any questions about these platforms, let me know in the comments below. Thank you. --- Source: https://simpladocs.com/resources/chatgpt-vs-superhuman-go-agents # Build your first Superhuman Go agent, step by step > A Go agent is a written prompt, a trigger and a set of tool permissions. This walkthrough builds three from scratch, and the PDF gives you the templates. **For:** People new to Superhuman Go who want to build their first agent **Format:** pdf **Video:** https://youtu.be/Yzc3EkyN9u0 ## What you'll be able to do - Know the parts of a Go agent (description, prompt, triggers, tool access) and what each one controls. - Write a prompt with a role, a reference section for IDs and numbered steps, so every run follows the same order and a changed ID takes one edit. - Pick a trigger (Gmail label, Slack mention or weekday schedule), set the permissions, then test and debug by running the agent and telling it to try again. ## What's inside - A reference section example that keeps a Coda doc ID and table ID in one place at the top of the prompt - A full prompt template with Goal, Context, Steps, Rules and Output format, written for a Monday client status email agent - A variables block that tells an agent to read a doc and table at the start of every run, and to stop and report if it can't - Rule lines you can copy, like "Never send. Drafts only." and "No due date? Write TBD." - The Always allow setting for write tools, so background triggers run without waiting on you - Pack SDK pointers (pack.addSkill, addMCPServer) and checklists for when you want to go past the editor ## Questions ### Do I need to write code? No. All three agents in the video are built in the Go agent editor with a written prompt, a trigger and tool permissions. The SDK pointers in the PDF are for later. ### What do the agents in the video do? They log tasks to a Coda tracker: one from Gmail labels, one from Slack mentions and one from yesterday's Granola meetings. The same build works for any tracker, since you swap the IDs in the reference section. ### Why did my agent find tasks but not save them? Check the tool permissions. Write operations default to always ask, which blocks a background trigger. In the video, the meeting agent found action items but couldn't save them until Superhuman Docs was set to always allow. ### Can I use Fathom or Otter instead of Granola? Yes. The video uses Granola for the meeting recorder, and the editor lists connectors for other recording services. If yours is missing, a connector can be built. ## Transcript This video is going to give you a deep dive, technically, in how to build Superhuman Go agents. So if you're looking for a quick, flashy video that's just going to show you different agents, this isn't it. I'm going to show you step by step how to build quality agents. So let's get going. First, let's start off with some context, because we're not just going to build any random agent. What I'm going to be doing today is hopefully applicable to a lot of you. This is a task list. Everyone here has a task list. This is actually a task list from my most popular video. It has over 10,000 views and over a thousand different downloads as a template. I built this task list in Coda probably four years ago, before AI, before agents were even a thing. So while it's a really cool task list, and you can see that video in the description below, I want agents to start adding tasks to this list for me. If you have your own task list, you could follow these same principles by having the agent add tasks to wherever you keep them instead of here. But let's go with that. The first two things that we're going to build an agent for are adding tasks from Slack and adding tasks from email. Oftentimes, of course, you're getting tasks from communications, and those are two of the most common forms of communication. So let's do that now. In Superhuman Go, to create a new agent I press this little plus button up here, and I get shown this screen. First, let's just give it a title. I'm going to call this my Master Task Agent. I'm going to give it a description. The descriptions are important. They're more than just there for you. What they actually do is, if you're just using the regular Go right here and you say "please add a task," it doesn't know yet which agent to use out of your many, many agents. So having a description helps route the generic chat experience to the correct agent. Let's ensure that we write a good quality description. I'm just going to go here to edit it and say: add tasks to my master tracker anytime I ask you to add tasks. We'll add tasks from Slack and email. That should be enough for a generic chat experience to route to this agent during appropriate times. Next up is the prompt. Let's do just a role and a goal quickly. Let's say: you are an executive assistant helping me add tasks from my Slack and email to my master task tracker. You always think about short and descriptive names. So now it's got a role and a goal. Let's give it a reference section. References are important, mainly for you. If you're going to put in IDs or URLs or things like that and you need to change them later on, instead of scattering them through a large prompt, it would be easier to put in a reference section at the top where you can come and change them over and over. We are going to be entering tasks into a Coda doc, so I'm going to give it a Coda doc ID and Coda table ID, and say: the document below and table below are IDs to Superhuman Docs (Coda) documents and tables. Always and only add tasks in this document and in this table. All right, so let's give it a doc ID. I'm going to go back to Coda and grab my doc ID here: copy doc ID. I'm going to go back to that other thread and push it there. Next we need the table ID so it's not guessing, and I'm going to grab that with these three dots: copy table ID, and put it back here. There we go. Now let's give it some steps. It's always good to give your agent sequential steps. It's not just randomly trying to accomplish its goal, but it knows how to accomplish its goal: step one, two. All right, so we just finished the full prompt. I'm going to quickly run through what we did. We have a role and a goal, just giving it high-level information when it starts its run about what it's trying to do and accomplish. Next I gave it a reference section that really just helps me put IDs into this larger prompt. If I ever need to come back and change them, instead of scattering them throughout, I have a single reference section. Lastly, I'm giving it four different steps. Giving your AI agents sequential, step-by-step prompts really helps them execute. They aren't just trying to randomly accomplish a goal, but they know which steps to follow in which order. First, I've asked it to determine the trigger source: whether this was run from an email or a Slack. Then determine a task name. The email or Slack message that triggered this may be lengthy, and we want a name for it. You'll see here, because I want a small name, and then I'm going to want a note section, so I'm asking it to come up with a smaller name. Then determine a due date. It may or may not have a due date, but it's going to try to anticipate and guess one. And lastly, we're going to input that into the Coda document and table referenced above. I also asked it to add the full communication to the note section, so it knows exactly where to put that, and it's going to increase consistency and reliability. So that is our description and our instructions, or our prompt. The two most important things. We've got two more things to really figure out, and then we're going to test this live. Those two things are your triggers and then your tools and access. It's important that we put both of these correctly. We can't put more than one trigger, so we're going to do that now. First, we're going to do "when a label is added to an email." I don't want every single email I have to become a task. I'm going to manually, as I'm working through my email, choose ones that need to become a task. This is synced with my Gmail, so these are my real Gmail labels. I'm going to choose this random Blue Ridge label. You might want to create your own label called "email task" or something similar, but I'm going to do that for now. Then let's add one more. Let's do an agent mention. What we're going to do in Slack is go to a thread, and then we're going to ask the agent in that thread to create a task from that thread. So we're going to say: if the agent is mentioned, and we're going to say General Biz. This is already connected to my Slack workspace. I think this is a bug, the fact that this is here right now: as of taping, Superhuman Go agents cannot be added to private channels. I know that's on their roadmap, but right now this is only showing public channels in my Slack workspace. Notice when I do agent mention, I can also determine who can run it: is it just me, or is it anyone that is in these channels? Right now I'm going to keep it just me. All right, I've got two different triggers. Lastly, I've got to think about tools and access. Web access: absolutely not, it doesn't need to access the web. Superhuman Docs: this is going to allow us to read and write into the actual task document, so yes, we need that. And then of course, because I added the label added trigger, it's automatically turning on Gmail, Outlook, and Calendar for me. This is actually not ready to go yet. You'll see this warning down here. It says that your background trigger runs this agent automatically, but some tools are set to ask before running. Right now, always ask is for write operations. If you keep that on, you're going to have to manually approve, and that kind of defeats the whole purpose of an agent. So I would choose always allow for these, and then it should be able to run all by itself. Let's save that. That's the Master Task Agent, and now I should be able to, from Slack or email, add tasks to my document. Let's go see it happen in real time. I'm going to add some Blue Ridge information to my different emails. Let's go Blue Ridge, and let's go here to Blue Ridge. I added those labels inside Superhuman Docs. Let's go back to Go and see those working. You'll see here two of them got triggered because of two emails. I don't need to see these happening, but if I ever want visibility into whether my agents are running, or if there are issues with it, you can come back to your tasks and see what happened there. There we go. We can see that it added this task due on October 2nd with a high priority and a source. Let's go ahead and see those actually added. There they are. We've got a high priority, we've got due dates, and if I close in here, you'll see that it has all of the information I need from the email as well. Amazing. Worked perfectly. Next up, let's go see it work in Slack. I'm going to go to Slack, and here I am inside of here. I'm just going to go randomly to this message, and inside of here I'm going to say: Master Task Agent, add this as a task. See how that works. Oh, there we go. Okay, you'll see immediately some eyes were added to it. That's, at least early on in these beta stages, the indication that it's actually working for us. So now we just have to cross our eyes and hope. If you don't see a response coming soon, you should expect a response. There it is. That's the response coming back. Great. If you didn't, of course, you could go back to Superhuman Go and see it run, and normally if it hits an error or hits something wrong, it'll show you right here. So let's go back and see if that task added as well. There it is: review Jordan's coverage. Amazing, awesome. Okay, so those were added. But let's try to build one more agent that's a bit different, that works on its own without me having to prompt it. One other place where your tasks probably typically come from, obviously email, Slack, and then meetings. What I want to do right now is have an agent trigger that looks through my meeting notes from the day previous and adds any relevant tasks there. So let's go and make one more, and let's call this the Post Meeting Task Bot. We're going to say: on a schedule, reviews all recorded meetings yesterday and adds tasks to a defined task tracker. Let's go to here: role and goal. All right, so now we've got a larger prompt. You'll notice that I have a role and a goal again. I put a bar, meaning a bar that must be met for an action item to be applicable. I don't want it to spam and fill my task list with a bunch of things. I can also tweak this bar as time goes on, if I'm noticing that it's adding too few or too many action items. I've got my reference section, and then I've got some steps. First, I ask it to determine today's date. Sometimes AIs don't work really well with dates, so it needs to actually calculate the specific date. I'm asking it to search Granola for any meetings that took place yesterday. Granola is currently our meeting recorder. If you use Fathom or Otter or any other recording service, of course you would use that instead. And I said if today's Monday, look at any meetings that took place on Friday. We're going to search through all meeting transcripts to find relevant action items and then add them to my task document above. Let's get a trigger. This is going to be a different trigger, of course. We don't want it to be triggered off an email or something. We want it to be going on a schedule. I want it to go on weekdays at, let's do, before I wake up, at 5 a.m. That's going to be fantastic. Next, I'm going to add Granola. There it is. I'm going to connect that and add that there. There are a lot of other connectors in here for other meeting recording services. If yours doesn't exist, they can always be built. All right, now that that's connected, I'm going to go in here and say read: always allow. That's all I needed to do. And there we go. Last thing about testing these: you could just press this "run this agent" button. Obviously I don't want to wait until 5 a.m. to record this video, so I'm going to go ahead and press run this agent to see what happens. It instantly just starts a message to this agent that says "I want to run this agent," but you'll see we can see it's thinking here. It's querying all my Granola meetings and more. So let's watch it run. Well, none for me. All right, let's try something else. Look at last Thursday, maybe I had more. Look at today instead. All right, you might not have to do that. I just want to be able to show you in the video itself, so we're going to see if it does today instead. Let's wait again. All right, there we go. It found some, but darn it, I didn't enable Superhuman Docs. That was a silly mistake of mine. So let's go ahead and enable that. Let's go to always allow, and let's go back and save that, and we're going to go back here. Let's say: try to add again. This is a good step as you're configuring and debugging your agents. You can just come back, change things, and then just tell it: try again, try again, try again, and it should be able to try those pieces. So let's go back to the Do More list, and we should see, there they are. Awesome. I'm getting a lot of different pieces, like "send Vicky the discovery questionnaire" with a bunch of notes. All right, so those are building agents. There are so many tips and tricks to building quality agents, from prompting to authorization to more. If you want a ton more resources, go to the description. We've got a huge PDF for you full of tips, tricks, and resources. All right, thanks. --- Source: https://simpladocs.com/resources/build-your-first-superhuman-go-agent # Write a Go agent prompt that runs the same way every time > One candidate email means a table update, a Slack message, a calendar invite and a reply. The PDF shows the prompt structure behind the agent that does all four from a single label. **For:** Ops and HR leads building Superhuman Go agents **Format:** pdf **Video:** https://youtu.be/ot_Gbq75u6g ## What you'll be able to do - Write agent prompts as numbered steps, so the agent does the work in the same order every run. - Keep names, IDs and lists in a doc table instead of the prompt, so a change takes one edit. - Trigger the agent from a label you add yourself, so it runs when you want and doesn't burn tokens on every email. ## What's inside - A prompt skeleton with Goal, Context, Steps, Rules and Output format sections, filled in for a Monday client status email agent - A Reference section pattern that holds doc IDs and table IDs in one place - A Variables pattern: read the active staff list from a doc table at the start of every run, shown with an onboarding invite agent - How to find the doc and table IDs (the grid-... values) your prompt needs - Which connector permissions to set to Always allow - Pointers for building the same agent in code with the SDK, plus checklists to run before you save ## Questions ### Do I need to be doing interview scheduling? No. The video uses interview scheduling because it touches a table, Slack, a calendar and email in one run. The prompt structure works for any multi-step agent, and the PDF also includes client status emails and onboarding invites. ### Which tools does the example agent connect to? Superhuman Docs, Gmail or Outlook, Calendar and Slack, with Superhuman Mail writing the reply in your own voice. ### Why use a label as the trigger? An email-received trigger fires on every message, including the ones you don't want handled. A label fires only when you add it, so you choose which emails the agent works on. ## Transcript All right, today I'm going to teach you how to build a Superhuman Go agent that does five or six different things across many different systems and could possibly automate away someone's entire job. Follow along with me as I show you how to build an agent like this step by step. To set the context, if you've ever worked in HR or dealt with interviews, you know that it is a ton of work. There are so many follow-ups and emails that you have to send. For example, you may get an email like this from an individual: "Thanks for getting back to me. I'm interested in the role. I'm free October 7th at 10:30 a.m. for an interview." This may seem simple, but there's so much that needs to be done. First off, if you are working in HR, you're going to get dozens, hundreds of these. You need to schedule those interviews during free times. You need to let your internal team know when this is happening. You need to create the actual calendar event and invite the right people. And of course, you need to keep your applicant tracking system up to date. There are a lot of things that need to be done just because of this one email. I'm going to show you how to simply add a label to this email and everything else will be done by an agent. If this isn't your exact workflow, that's okay. This video is going to cover general principles for building agents that would allow you to do these kinds of multi-step processes. I'm going to go to go.superhuman.com. Once I'm at go.superhuman.com, I can see my past tasks or I can, of course, build an agent for myself. I've already started building an agent, so I'm not going to press this right now. I'm going to go to the one that we've already started building. When you have an agent set up, this is the configuration screen. This is where you're going to actually build the agent itself. You've got a name for your agent. Let's call it the Interview Scheduler. We're going to give it a description: it's going to schedule interviews, it's going to respond via email to the candidate, it's going to send a Slack message to the internal team, create a calendar invite, and more. The next part of this agent, and the most important part of any agent really, is the prompt. The prompt tells the agent what to do again and again. This prompt is long, but because it's the most important part, I think it deserves its own screen. I'm going to break this down and show you why I did what I did. Don't worry, I'm not going to take ten minutes to run through this. It'll be done quickly, but it is really important in building your agent. As far as principles go, here is our entire prompt. This is everything from a role and a goal all the way down to step four. Let's go through each one of these one by one and see what I did and why. First off in my prompt, I give the agent a role and a goal. It's just that high level, telling the agent right away: this is your role, this is your goal, this is what you're going to do. Then I have a reference section. The idea of a reference section is simply that: things for the agent to reference. Now, I could scatter these throughout my steps, but having a specific section makes it easier for me as a human. If I need to come change these later, I can easily find them in the reference section and change all those pieces. Really, this is less for the agent and more for the human if they have to change this information later down the road. Next, you'll see I actually put the words "step one" into the prompt itself. This isn't just here for a glorified slide. I wrote step one. It's good to give your agents sequential steps. Don't just say, hey, you need to schedule an interview and send a Slack message. What if they do those in different orders? So first, I say step one, and I'm letting them know exactly what they need to do and where. First, I tell them that all interviews are kept track of and scheduled in a table with an ID of this grid. That is inside of this Coda doc here, right? This is where me and my team are keeping track of every applicant to our job. We can add new ones, we can comment on them, we can change them. The agent is going to interact with us here as well. I think this is generally just a good principle when you build agents: they shouldn't just act invisibly in the background on their own. Rather, agents should have a surface where they can be transparent about what they're doing and collaborate alongside you and your team. Docs is a wonderful surface for this. I can work and comment in here, and then the agent can come and collaborate alongside me inside of the doc. Here we are back in our prompt. I'm telling it to keep track of it in here. When a label is added to an email, and we'll show this live at the end of the video, all working through, I say use the metadata about the email to find the sender's existing row, so it knows which row to actually update. Then it says when you find the matching row, update it with the new date and time of the interview. So it's going to pull out the date and time of the interview from the email and update it there. Step two is about sending the Slack message. First, I give it the ID of the Slack channel that it should send its message to. Then I give it a format. Notice I use these curly brackets. I could just say, hey, send a message, and it would send whatever it thinks appropriate. But it's good to help guide the AI and tell it exactly what it should be doing. Using curly brackets like this tells the AI to insert variables there. So it's going to say the actual person's name, as well as the date and the time that the interview is scheduled for. For step three, I said schedule the actual meetings with invitees in Google Calendar. I need to include the person who sent the email and the interview committee. This part, I think, is important. I want every single calendar invite to include the person who should be invited, as well as the interview committee. You'll notice that I'm not holding the interview committee and those people's names inside of the prompt. I'm actually holding them inside of this document here, the interview committee. Again, I call this a variable: something that might change. Maybe someone's sick one day, or maybe you hire new people who are on your interview committee. Instead of having to go into my prompt, find that, and change it every single time, I just say the interview committee is in this table. I can then change it here inside of my applicant tracker, and every time the agent runs, it's going to read afresh who that interview committee is. So using variables inside your prompt is important. If you want more tips and tricks like this, we actually have a huge PDF full of resources, tips, and tricks in the description below. You can go grab that and get a lot more information on this prompt construction. Let's look at the last piece that I did inside of our prompt. Step four, I said respond to the email that originally triggered this. Let the sender know that their interview has been scheduled. Notice that I didn't give it a format for how to respond. This is using the Superhuman Mail MCP, and the Superhuman Mail MCP actually knows my unique voice. It catalogs all the emails that I send. So I already have trust and confidence that it's going to send an email that I feel is appropriate. Again, if I didn't want to worry about that, I could use the same format I used for my Slack message, giving it an exact format of how it should send that email. So that is our prompt. There are only a couple more things that we need to do in order to get this agent going. Next up is my trigger. There are a lot of triggers. Over here on the left-hand side, you'll see I have email received. I could do that, but I just don't want it to trigger on all these different emails and have useless runs. I want to be smart about the tokens and usage that I'm consuming. So I'm going to use label added. This is a way that I can quickly and manually trigger these on different emails. This is connected with my Gmail specifically, so if you need new labels, you have to go add them in your mail provider. I'm going to choose interview and I'm going to say add. I've now got an appropriate trigger. Next up, I need to add my connectors. First off, I need to add Superhuman Docs, because it's going to be writing and reading in that doc. It is going to be writing, so we need to change this to always allow. For Gmail, Outlook, and Calendar, we need to change this to always allow. And lastly, it's going to be sending Slack messages. So let's go and add Slack. Notice here that you can just search these, and there's Slack. Add that, and X out. All right, the agent is saved and ready to run. All we're going to need to do now is go trigger it. Triggering it is really easy. I'm in Superhuman Mail. I'm going to press the letter L on my keyboard, which adds a label. I'm going to add the label interview, and we should be able to go back here directly and see that running. You'll see this started on the left-hand side. It's running right now and working for us. If there are no issues with my connections or account pieces, it should work, and we can see what it's doing. All right, here the agent is managing table rows, creating or updating events, and more. Let's go in and see what it did while we're waiting. Next interview date. There it is, it changed it. Let's see the activity itself. Yep, today at 1:26. It is 1:26 PM. You'll see that that was changed and those were updated. So that is the agent actually working inside of our document. You can also see here is our Slack message that was sent, and here is the email that was sent back to her: "Hey Jordan, October 7th works perfectly. I'll send over a calendar invite shortly so you have all the details." Again, that was all done by simply adding the interview label to the email. If you have any questions about building agents or how I constructed my prompt, let me know in the comments. And of course, if you want more tips and tricks on agent building, grab it in the description below. --- Source: https://simpladocs.com/resources/go-agent-prompt-tricks # Get your morning briefing before you sit down > Every morning starts the same: check the calendar, check email, dig up context on who you're meeting. This agent does it on its own, before you sit down. **For:** Founders and account leads who want calendar, email, and meeting prep waiting for them each morning **Format:** pdf **Video:** https://youtu.be/bvwF7-PKlLE ## What you'll be able to do - Build a scheduled Superhuman Go agent that runs on its own every weekday morning at a set time, no manual trigger needed. - Give it standing context about you once, your role, your company, so it never has to be re-explained on every run. - Have it check your calendar for external meetings, pull past meeting history from Granola, triage your inbox, and write the result into an existing doc instead of a new one every day. ## What's inside - The doc ID and table ID format so a scheduled agent writes to one existing page instead of creating a new document every run - A ready-to-copy prompt for a Monday status-email agent, the same reference pattern used to point an agent at a live Projects table - A ready-to-copy prompt for an onboarding agent that runs against an Onboarding table and books session invites automatically - Notes on Always allow versus Always ask, the setting that decides whether a scheduled agent can run unattended - SDK snippets for adding a skill or MCP server to a custom pack ## Questions ### Do I have to trigger this every day myself? No. Once it's saved with a scheduled trigger, it runs on its own on the days and time you set, no chat message needed. ### What if I use Outlook or Gmail instead of Superhuman Mail? Swap the connector. Add the Outlook or Gmail calendar connection in the trigger's connector list instead of Superhuman Mail, everything else in the setup stays the same. ### Why does the agent need Always allow instead of Always ask? A scheduled agent runs while you're not there to approve anything. Set write permissions to Always allow, or the run pauses and waits for someone to manually approve it. ## Transcript All right, today I'm going to show you how to create scheduled Superhuman Go agents. If you're unsure of what Superhuman Go is, you can look at some of my other videos for some introductions, but Superhuman Go agents are these powerful AI agents that can collaborate with you to do your work and just get your work done for you. So today we're going to build an agent that has a scheduled routine. It's going to go off every Monday, or every Tuesday, without you needing to do anything. Let's go with advanced setup first, and this is what you're going to see: this is where you can manually build an agent. First off, what you have is a name. We're going to build a daily briefing agent, which should be applicable to any of you that have a job, you come in and sit down for work first thing in the day and you want to know what the heck should I do today, what emails did I get, and what's on my calendar. So we're going to call it a Daily Briefing. And next we're going to give it a description. The description here actually does matter. You may think it's just quick for you to visualize and know what it is, but it's actually going to be used later for general Go agents to find and trigger this agent. So I'm going to copy this down, you'll see I put "runs my daily sales briefing, use it when I ask for a morning brief, a daily briefing, what my day looks like, or prep for today's meetings." So the description, if I am inside of this new task and I generally just say "run my daily briefing," Go has to figure out should I use an agent for this, what should I actually do, and it's going to determine if any of the agents that you own here are relevant to what you're asking it to do. That's what the description does. The description will help Go determine which agent it should actually use. If you're in daily briefing you can just ask and it's already going to know, but of course if you're using your new task it needs that. So let's go back to our daily briefing and keep moving on. We have a good quality description here already. Now we need the instructions. The instructions are the larger prompt that is actually going to tell your agent what to do every time that it executes. So I have a larger prompt saved here, and let's paste it in and talk about the different aspects of it. So first off, I'm giving it context about me. Every time an agent runs, it runs fresh. It doesn't actually have a memory like we think of human memory, and so I'm going to give it some information it needs every single time. Luckily I don't have to ever retype this, I type it once and it's saved forever. Lets them know that I'm the founder of SimplaDocs and we do enterprise Coda or Superhuman Docs slash Go implementations, custom workflow, and more. Okay, then I'm going to start telling it what to do. Say Go, basically, you know, look at today's calendar for me, do some external meeting prep. I'm saying specifically if you find meeting invites that have external invitations on it, people not from my company, this is what I want you to do. I'm also going to use our meeting recorder, Granola, to search and determine if we have met with this individual company in the past. So I'm going to be doing a lot of things: searching the web, looking at my calendar, looking at past meeting invites. It's going to do a lot of actions. Last thing I'm going to have it do is an email triage, understand what my email is. It's going to build a suggested task list. And then lastly, I think this part is really important: it's going to do all this research, it's going to look at all these things, and now we have to determine what's the actual output, what do you want to see in the morning. There's a lot of different options. What I have right now is, I'm saying a new page in a Superhuman Docs document. I don't want to create a new Superhuman Docs document every single time, so I've actually given it an ID to an existing document, and then I told it what specifically I want in it. So let's go ahead, now that we have our instructions laid out and we're using IDs to give it an ID, I'm going to add a trigger, and this is where that scheduled trigger comes in. If you go into docs, you'll have different trigger options here. These are always growing at the time of creating this, this is what is available, but I'm going to say repeat, actually, on weekdays at, let's do it at 8am. Let's do it a little earlier in case I start work, I want it to be ready for me by the time I step into work. I'm going to add this. There, now we're actually not ready to run this yet, we have to connect the appropriate connectors. It will not be able to use Granola. You'll see here I said "use my meeting recording Granola," it's not going to just be able to use it just because I asked it to. I have to authenticate and tell it to use that. So first off, I know it needs to use Superhuman Docs, right, I know that it needs to input information to a document. You'll notice when I first turn this on it says write is always ask. If I want this to trigger automatically every day, I can't give it manual approval, so you'll see it gives you a warning here as well: some tools are set to ask before running and it will pause until someone manually approves. I don't want that, so I'm going to allow it to work by itself. I'm also going to allow it to search my mail and my calendar. This is if you do use Superhuman Mail, then you can turn that on. If you don't, let's say you use Outlook as a calendar, right, you can go ahead and you can search for Outlook Calendar and add those. So if you use a different calendar, you're going to add those connections here. But the connection that I want to use is our Granola connection. I'm going to add it, see that it is added and connected, it is set to always allow, and I might need to go to its settings to re-authenticate. I can test that if I need to. But now I've got it connected to my mail, to my calendar, to docs, and to Granola. If you want to test it, you can press run this agent, but as it is, if I press save, this agent will run every weekday at 7:30am and provide that briefing to me in a new document. So let's press run agent and see what happens. All right, so you're going to see here that it actually did create the daily briefing. We've got a lot of information here available for me as we go. So that is just a quick look at scheduled Go agents. I'm going to have a lot of other videos on how to use Go agents side by side with docs, by themselves, with proactive triggers as well. So take a look at my channel for those other videos, and let me know if you have any questions in the comments below. Adios. --- Source: https://simpladocs.com/resources/scheduled-superhuman-go-daily-briefing # Catch off-brand writing before it's sent > Your brand guidelines live in a doc. Nobody checks it before hitting send. This agent reads the doc for them and flags off-brand writing while they type. **For:** Ops and comms leads rolling out brand-voice consistency across a team **Format:** pdf **Video:** https://youtu.be/1nD0Zwe8cp4 ## What you'll be able to do - Set up a Superhuman Go agent that watches email and docs, not code, not social, not search, and flags off-brand phrasing while your team writes. - Point the agent at your live brand guidelines doc in Coda or Superhuman Docs, so an edit to the doc changes the agent's feedback without touching its instructions. - Get a specific rewrite for every flag, not just a note that something's wrong. Click it and the line updates. ## What's inside - The doc ID and table ID format for pointing an agent at one specific Coda table instead of a whole workspace - A copy-paste prompt for a Monday status-email agent that drafts one Gmail email per active client from a Projects table - A copy-paste prompt for an onboarding agent that books session invites for new hires from an Onboarding table - Notes on when to set a trigger to Always allow versus Always ask - SDK snippets for adding a skill or MCP server to a custom pack ## Questions ### Does this only work in Superhuman Mail? No. The video demos it in Superhuman Mail, but the trigger watches the page you're typing on, so it works the same way in Gmail, Outlook, or Coda. ### Do I have to update the agent every time the brand guidelines change? No. The agent reads the Coda or Superhuman Docs page live. Edit the guidelines doc and the agent's feedback changes on the next check, no agent edit needed. ### Will the agent send emails on its own? No. It flags writing and suggests a rewrite you click to accept. In the video, the Superhuman Docs MCP permission is set to always ask, so it isn't writing or sending anything without you. ## Transcript All right, today we're going to be building a proactive Superhuman Go agent. These agents are different than any agent you've ever seen before. If you're accustomed to agents with ChatGPT or Claude or any other software, no other agents I've seen can do this. So follow along with me as we build a proactive agent that acts before you even ask. To set the context, we're going to be building an agent called Brandman. Imagine that I am an employee at a B2B software company and I'm writing to customers. Well, I don't want to just write however I want to write. There's certain brand and tone guidelines that I need to follow in order to be on brand. So we want to ensure that we enforce that across all of our employees across our company. So how we're going to do that here is we have a brand guideline. I have this document that tells my employees how to write. But the problem is there's a lot of information in here and my employees don't always follow it. Sometimes they just go into their email and send off emails. So how are we going to get people, while they're writing, to follow these guidelines? What we're going to do is go back to Superhuman Go and create an agent called Brandman. Our description here is to help ensure that our customer support and customer-facing roles communicate on brand. The descriptions are important. They do help other agents know when to orchestrate or use this agent on your behalf. So I'm going to give it some instructions. First, I'm just going to give it a role. The company that we're pretending to be is Fernway. So this is Fernway's brand voice editor. You watch what the user is writing and help them match the Fernway brand voice. And this is how we give it our brand guidelines: I could just put the entire brand guidelines into the instructions here, but it's hard to change. What if your brand guidelines change over time? The beauty of keeping them inside of this document is that your entire team can come and collaboratively update it whenever they need. And we're going to ensure that our agent is dynamically referencing that live document. So how I'm going to do that is I'm going to say the guidelines live in a Coda document. Always use the Coda or Superhuman Docs MCP to read them before giving any feedback. In order to make this agent faster, I'm going to specifically tell it where to find that information. So I said, please use the document ID and use the page ID. If you're unsure how to get those, you can actually get those up here: doc ID, or go to the page itself and you should see a copy page ID. If you don't see those, go to the comments down below. There's some more information about how you can find that for your account. It may not have that turned on, so check out the description below for more resources. So I've got this here now, and back in my instructions I'm going to tell it to use the content read tool, request markdown content. I'm going to tell it when to act specifically. I'm going to tell it how to give feedback. This is important because our agent will proactively, as you're typing, come in and tell you what you should do differently. We don't want the agent to just be like, you suck, write differently. We want it to give specific feedback, and not just feedback, but we're going to suggest a rewrite of that phrase or sentence. So it's not only going to tell you which rules you're breaking, it's going to be able to instantly change your writing into an on-brand style. All right, so here we go. We have triggers down here. It's a proactive assistance while writing. Let's delete that though and show you how we actually built that. So we're going to go to add trigger and there are a lot of triggers here. They are growing at the time of recording. These are the ones available, and we're going to choose the proactive assistance while writing. It is active. You can change the color here if you'd like. Purple. Red is like warning, warning, warning. I'm going to choose purple because I like it. Where would you like this agent to help you? I'm going to say email, docs, not in coding because I'm not talking to customers while I'm coding. I'm not doing it in social media and we're not doing it in my search, my browser. So I don't want it to trigger just all the time. I want it to trigger most likely when I'm talking to a customer. If I find that this triggers too often, what you can do with your proactive triggers is come down to the custom instructions and give it more information to restrict when it's going to trigger, or to make it trigger more often. But I think this is fine for now. So what we're going to do lastly is turn on the Superhuman Docs MCP. I've asked it to use the MCP in order to grab that information. It won't be allowed to, or able to, unless you turn this on. So let's turn that on. And this says always ask, for writing. We're not having it write at all, so it doesn't need to do that, but we can keep it always ask for now. All right, and with that, we now have our proactive agent ready to go. I'm going to go ahead and save it, and then let's move on. Now the agent is saved and I'm going to move into email here. I'm in Superhuman Mail right now, but this would theoretically work on any email client, whether you're Gmail or Outlook or wherever else you are, it should be able to work. So I'm going to go ahead and first show where Go is. This is my desktop version of Go. You'll see I can open Go here and just chat with it. Or the other part down here are the agents for writing. You should be able to see them while it's working. So I've got a message to a customer. Let's say, message to customer: I'm going to say, "Sorry for the inconvenience. The login issue impacted some users this morning." These first things that you're seeing are Grammarly suggestions, but let's go here and see what's happening. You'll see Brandman is currently checking, and it says it has an issue. If you see this, there might be an issue with you here: page ID appears invalid. So it's giving us some information about what might be wrong in our configuration. All right, so it's giving us the information that the page ID is invalid. So we can actually go back, and it should be able to work without that. So let's go and take the page ID out, and I'll say, "There is only one page in this document, read that page and use its guidelines to provide all feedback." Let's go ahead and save that. All right, Brandman has been saved. Now let's go back here and we're going to see Brandman checking out our writing again. And there we go. You see five issues. This will not normally show up unless I have it open, but you'll see there is our purple underline. It says, "Sorry for the convenient inconvenience." If I hover over it, you'll see that it's coming from Brandman, and it's giving me a rewrite: "This morning, some customers had trouble logging in." Not only does it give me the rewrite that I should do, but it also gives me some information: this word breaks word choices. The guidelines say not to write "sorry for the inconvenience" and to say what happened and what we're doing about it instead. So this is where I think these agents are great, because again, it's not just asking me to go rewrite it or copy and paste from some other platform. I can simply click and it's done for me. The login issue, instead of "resources" I should say "team," and instead of "users" I should say "customers." So let's try one other and see if it will trigger again for us. Let's go. I'm going to grab from my clipboard. I'm going to paste in an email. This is for a launch of product email to all my customers. So I've got my information here, and you'll see right there. It took about maybe three seconds that time, but it's starting to give me a ton of different information: inclusive greeting, "everyone." I want to say change "9am PT." So all of this information is coming from my proactive agent. What is good about this is oftentimes your employees may not have the due diligence to go check brand guidelines, come back, synthesize their writing with that, and understand what's out of sync. I also don't have to take this and copy and paste it into ChatGPT and ask it to analyze against brand guidelines and paste in the guidelines. This agent will simply work for my whole company proactively to give me the writing that I need to do. So those are proactive agents. There are so many types that you can use, because you can use other connectors at the same time. If you have any questions about proactive agents, or if you just want more resources and information on them, head to the description below to see them. --- Source: https://simpladocs.com/resources/proactive-brand-voice-go-agent # Let Claude and ChatGPT Work Directly in Your Docs > If you're copying data back and forth between ChatGPT and your docs by hand, the MCP lets Claude or ChatGPT read, write, and build inside Coda and Superhuman Docs directly. **For:** Coda and Superhuman Docs users who want their AI tools to read and write documents directly, not just chat about them. **Format:** coda-doc **Video:** https://youtu.be/CcuufVFlIn4 ## What you'll be able to do - Ask Claude to build a full Coda document, tables and all, instead of dropping in text you have to reformat yourself. - Set per-tool permissions so write and delete actions need your approval before anything runs. - Connect outside context, like your calendar, so the AI can act on more than just the doc in front of it. ## What's inside - The full capability matrix: all 81 things the MCP can do inside Coda today, and what it still can't - Tips and tricks for using the MCP safely, including how to set tool permissions in Claude ## Questions ### Does this work with ChatGPT, or just Claude? Both. The video uses Claude, but the same MCP connection works in ChatGPT and any other AI tool that supports MCP. ### Can the AI delete or change things without me approving it first? Not unless you let it. Every tool, including write and delete actions, has its own setting: allow, ask first, or block. ### What can it actually do inside Coda? Create pages, tables, columns, and formulas, not just drop in text. The doc has the full list of 81 things it can do right now. ## Transcript We're going to talk all about the MCP in Superhuman Docs, or Coda. I think it is one of the most transformative things I've seen in Coda in the last eight years. Maybe I say that a lot, but I really do believe it this time. Let's get to business. So, what is an MCP, first off? If you're a developer, you're probably going to hate me for this definition, but I think the easiest way to understand it as a non-developer is: it simply allows AI models, Claude, ChatGPT, to interact with your software and systems. There's going to be a different MCP for each software, so there's an MCP for Superhuman Docs. In this video, I'm going to show you how the MCP works directly right here inside of Docs, really quickly and easily. You don't need any other tools or any other magic, you can do a whole bunch of stuff here. Then I'm going to show you how the MCP works inside of Claude, and how you can put your work on auto. And then I'm going to give you some best practices in terms of how to use it safely. So let's look at this first. I've got a prompt here. If you want to use the MCP inside of Docs, just use your little purple stars down here in the bottom right-hand corner, and you can ask it to do anything. So let's ask it to search the web and write an article on this page that explains what an MCP is. Right now, at the time of recording, it does have access to the web, but not other tools yet. By other tools, I mean it can't access HubSpot, it can't access Salesforce, it can't access Slack. It can just access the doc itself and the web. So we're going to go and watch it work. As it does work, note that the MCP can do all sorts of things. I've asked it, for example, to include an interactive button at the bottom of the article to indicate whether or not someone read the article, and to create a quiz with multiple questions. So it's not going to just dump text content, and that might be what you're used to as a user of AI models: text content. But the MCP is going to be able to do things like create tables, create columns, write formulas, almost anything that you can do inside of Coda, the MCP is going to be able to do as well. It is preparing article content, so it's going to drop that in in just a second. But as you're waiting: if you're wondering what the MCP actually can do, beyond "almost everything," I do have a capability matrix, everything it can do. Here is an exhaustive list of things that it can and cannot do, 81 different things that it can do, and some things it cannot do, like automations, certain things with the UI, and certain things with table view. If you want this exhaustive list of things it can and cannot do, there's a link in the description below. So let's see what it did for us. It went ahead, and it's written an article now that talks about what an MCP is. This is text content, as I mentioned, but it also dropped in a table. I can also ask it to do things like modify that table and add eight more questions, and you'll see it's thinking, and it's going to use different tools it has in order to add those different rows. It's taking quite a while, but I can expand here and see what it's actually working on, it lets me know what it's doing and why, like managing columns. But you'll see it did add those eight different things. So you can continue to chat with this Docs AI over here on the right-hand side to create your documents. Now we're going to jump into Claude and see how the MCP works in Claude. Note that this would work in ChatGPT or other common ones as well, we just use Claude, so I'm going to show you that. I'm going to first show you one important thing about how this MCP works inside of these systems, that's really important for privacy and control. If I go down here to my settings, to my connectors, and Coda, you're going to see all the tools. The MCP is actually a bucket of tools, these are the tools or things that the AI is going to be allowed or able to do. I have three different options: I can allow it to run, I can say it needs approval to run, or I can block it entirely. So I can go in a granular way, and I can say, allow everything. Now, when I run a query inside of Claude, it's going to be able to use all these tools without explicit permission. Or you could say, actually, delete comments is a destructive action, these write and delete tools are more destructive, so I'm going to say you need approval, and then, of course, you could also block them entirely. So it's worth it to spend a couple minutes inside this settings area to ensure that no destructive or crazy things happen. I'm usually more on the always-allow side, but definitely take things like delete pages and put them at need approval, so it doesn't accidentally delete a bunch of stuff or delete whole documents. So that is the MCP inside of Claude, and how you can actually tweak how it works. So let's go watch it actually work in Claude as well. I'm going to go grab this prompt back here inside of this document. What I'm setting the stage for here is to show you why using it in Claude might be better than Docs AI. So, setting the stage: let's pretend that I'm a busy employee with a ton of calendar events this week, and I need to quickly know what's coming up, who I'm meeting with, and what I should focus on. I'm going to ask Claude for a look-ahead, a week preview for this week. It will give all my meetings at a glance. Based on the calendar invite information, name the top three meetings which seem to be of the highest priority, and create it as a Coda document using the MCP. Notice that I'm telling it, and giving it some information, like: create tables configured as calendars for an at-a-glance view. So I'm using some Coda-specific vocabulary, so it doesn't just go wild and create something weird, I want it to create something curated. I also told it that it can use Google Calendar, web search, and Coda. So one thing I am using is Google Calendar. If I go ahead and use Docs AI, it does not have access to my calendar, it doesn't have access to other systems. So when I'm using this inside of Claude, it's going to be able to find and use those things. So here we go, and I'm going to now paste it and see what happens. You'll notice that it's searching available tools, it's trying to find out what it should do. It's listing calendar events and invites, it's pulling the list of users and calendars. So it's doing a lot of pieces, and this does take a while and can take quite some time, because I've asked it to do a lot. I've actually done this exact same prompt just a little bit before, and I have a doc for it. This doc has not yet been touched by me, this was completely created by the MCP. So notice here, the MCP could do far more than just create a table or a page, it can create whole documents and whole systems. Here is what it was able to create: a week-at-a-glance. Let's go back and actually find those rows that it created. You'll see here it created rows based off of my calendar, it found a discovery call with Ramp. It also provided background on the individuals that I'm going to meet with, here's key people that I'm meeting with. Note that this is all fake, these were all pretend events that I created on my calendar. So what it did is it did some research, and it let me know who each of these individuals are: hey, I'm meeting with this guy, this is who he is. It gave me a whole calendar as well, with sourcing and caveats, and the top three priority meetings. So this is why using the MCP, especially in Claude or ChatGPT outside of Docs, can be really, really powerful, because it can use and connect to other tools. And then, if you're using it correctly, you can also run these on scheduled tasks. For example, I could create different scheduled tasks that actually create these weekly write-ups every single Monday. So that is your intro to the MCP. It is just an intro, there is so much that the MCP can do, and so much that we at SimplaDocs are using it for internally. If you want to know more about that, go to the description below, you can get access to a PDF and some resources about some tips and tricks on using the MCP. --- Source: https://simpladocs.com/resources/mcp-tool-permissions-demo # Give another team the rows they need, and nothing else > You want your closed won deals in the account team's doc without handing them the whole pipeline. Coda's Cross-doc does that once you know its quirks. **For:** Ops leads sharing Coda data across teams **Format:** coda-doc **Video:** https://www.youtube.com/watch?v=lBRzjrgNwQY ## What you'll be able to do - Sync only the rows and columns another team should see, so deal values and private rows stay in the source doc - Set up two-way sync with the right sync owner, so people can edit without each connecting their own account - Raise the 1,000-row default and set an hourly refresh before a growing table quietly stops syncing new rows ## What's inside - A plain-English explanation of what an MCP is - Four demos: MCP inside Superhuman Docs, in Claude and ChatGPT, on autopilot, and in GO - A deep dive on everything the MCP can do in Docs ## Questions ### When should I use Cross-doc instead of a filtered view? Use Cross-doc when some rows or columns have to stay private from the other team. If everyone can see everything, a filtered view in the same doc is simpler: no hourly refresh, no row limit, no extra configuration. ### How often does a Cross-doc table refresh? Hourly at most, usually a few minutes past the hour. Edits made in the synced table go back to the source doc right away, and each edit also pulls in newer values from the source. ### Can people edit synced data without access to the source doc? Yes, if the sync owner is set to shared. Their edits go through the sync owner's account. On private, each person has to connect their own account first. ### Does everything come through the sync? Most things do. Images and some advanced objects in canvas columns don't, and relation columns show only their display value unless you sync the related table too. ## Transcript Today we're going to cover everything you need to know about Cross-doc, which is the most used pack across all of Coda. This is a long one, worth every minute. Buckle up. First off, what is Cross-doc? Cross-doc is a pack. If you're not familiar with packs, packs are Coda's word for integrations. There are over 600 integrations with Coda currently, and that is growing. Cross-doc is the way to connect two documents, to share table data from one table into a different Coda document. There are a ton of idiosyncrasies with it, though, and best practices around how to use it that we're going to go over today. We've learned these across five years consulting with our clients, so we have a lot of information about how to use it well. So let's start looking at it. What I have here is an opportunities table. This is a made-up CRM: opportunities in our pipeline that we're trying to close. Let's say I want to take my closed won deals and share them with a different team. How can I take just the closed won deals and share that information to a different document? Cross-doc. So let's go to our different doc. Here we are in a completely different Coda doc, and it only has this one page. In order to get my opportunity data in, I'm going to install Cross-doc in this doc. Notice that installing Cross-doc doesn't make it available across your whole Coda workspace. You have to install Cross-doc as a pack individually, doc by doc. When I go to insert packs, it's the first one up here because it's the most used. You can also search for it. I'm going to add it to my doc for free. When I'm in here, you'll see at first I've got building blocks. I can do some different things with buttons here, and we'll talk about those later. The most important thing to know are tables, though. This is how you bring in information from other documents. Right here are all my documents. If you've got thousands of documents in your workspace, you'll probably want to search. What you see at the top level are the documents in your Coda workspace. When you find a doc, you expand it, and it loads all the tables in that document. From here, I want to bring in my opportunities table. I click on it and drag it into a page. I'll make a new page called Closed Ops, take my table and drag it in. When you do, it opens this new screen, called the Cross-doc configuration panel. There's a lot to go through here, and it's really important, so let's break it down step by step. First off, it's giving you a preview. By default, Coda will bring in the whole table, so in the configuration panel you decide what you actually want to bring in. There is an advanced section, and we'll go over that in a second. The intended workflow is that you come in here and decide first what rows you want to bring in. We want rows that, using this filter, have a stage of closed won. It gives you a preview of the rows you're going to see. You can add any number of filters and make them as complex as you'd like, but right now we're just looking for closed won. Lastly, columns: you can choose column by column what you're going to bring in, and include or exclude any of them. Now we press Add to doc. This can take up to five minutes for large tables and large docs, so go grab a cup of coffee if you need to. Our document is pretty small, so it should come up fast. Our table is synced, and there are a couple of things that are crucial to know. First, you've got these columns, and there are also other columns that are hidden. One shows you the row URL, the URL of the row itself in the other document. We call that the source document: it's where this data lives. Another shows what sync account it came from and whether or not it was synced. These are advanced columns we can get into later, but for now just know that if you don't see the column you're looking for, it may be hidden. Next up is the configuration panel for this table. There's the configuration for what is synced, under Change what syncs. If I wanted closed won and proposal sent instead of just closed won, I could change that there. Then there's what we can do once the data is synced in. First, refreshing the table. How often does this table refresh? By default, it's set to manual. You can set it to daily or hourly, and hourly is the most often it can refresh. Anyone can also come in at any time and refresh it. Hourly typically happens around every hour on the hour, so 10:02 or 10:03 AM. Under the advanced section, by default, this only syncs 1,000 rows. Your tables might have more than 1,000. If they do, you'll want to change this to 10,000. I normally change it to 10,000 right away, because I don't want to get into a situation where my table eventually grows past 1,000 and I forget to do it. Keep unsynced rows: you don't really want this on. It makes sense for other packs, but not for Cross-doc, so keep it off. If you turn it on and a row is deleted in the other doc, the row sticks here, and that's where you'd see the synced column show false. So far, then, we've set the sync to hourly so it refreshes often, raised the limit to 10,000, and kept unsynced rows off, which is what we normally need. Before we talk about editing, which is a whole other world, let's talk about how this table behaves. Because it's in this doc, it's like any other table in your document. You can turn the display into cards, a detail view or a chart, or whatever else you want to do with it. You can make connected views, so one view is a chart and another is a table. And the most important thing you can do is add what I call local columns. If you look at this column, you'll see that special square symbol, which shows it comes from our source doc: it's been synced in. But I can add new columns here, and this is called a local column. You can see it clearly when I go through all the options: symbol, symbol, symbol, and then this owner column has no symbol. That means it's a local column. A local column will not show up in your other doc; it lives here. These are all our closed won deals, so we'll hide the stage column, and I might want to give each deal an account owner. Now I can give this one to Scott, this one to Daniel and this one to Aaron. You can add as many local columns, formulas and buttons as you need. We can't fundamentally change the synced columns, because they exist in the source doc, but we can rename them. If I rename this to "Deal value!", note that that's a local name. The column is not renamed in the source doc. If we look back there, deal value is still called deal value, and there's no owner column. Back in our other doc, I'll normally hide these columns because they're annoying, and rename the table to Opportunities. It looks a little cleaner, a little more like a regular table in Coda. By default, synced columns are not editable. You'll see that when I click on one and try to edit it, I can't. But I can turn on two-way sync. Let's go to options, see all options, and turn it on. That makes these columns editable like any other normal Coda column. There are two options to set for editing. First, you decide when your edits become available in the other doc: do we send them immediately or manually? Right now it's set to manual. Let's rename this one Green Solutions and set the deal value to 80,000. You'll see these little blue triangles. They mean there are edits in this doc that haven't been sent to the source doc. If I go back to the source doc and filter to closed won, so we're looking at the same set, the old values are still there. Because send edits immediately is off, I have to come up here and choose to send. That runs a quick call. It's not literally instant; it takes as long as it takes for those blue arrows to disappear. Back in the source doc, the changes are there. Now let's turn on send immediately. If I change this to Retail Solutions, it still shows a blue arrow while the edit is going through, but I no longer have to press send. It sends for me, and it's done. The second option is the sync owner: how are edits sent back? Coda doesn't assume that everyone has access to the source doc. On private, it lets me edit because I have access to the source doc, but any other user who tries to edit will be asked to connect their own account first, and their edits will show up as themselves. If you have a very large team, that can get obnoxious, because everyone has to connect their own account. And if not everyone has access to the source doc, you might need to set it to shared. On shared, editors in this doc can edit the table using the sync owner's account. So no matter who comes in, anyone can edit these values, the edits show up in the other document, they don't need access to it, and the edits show up as yours. That is Cross-doc two-way sync. One other important note: some columns are not editable. In our source document, this notes column is a canvas column, which can hold a lot of things, like images, subtasks and grids. Canvas columns are a more advanced column type, and because of how many kinds of objects they can hold, Coda doesn't let you edit them on this side. If you've stuck with me this long, amazing. You're probably going to be interested in the rest, because we're getting into the nitty-gritty details of Cross-doc. On Green Solutions, I added all this extra content in the source doc, and it isn't here yet. That's because changes in the source don't appear in the Cross-doc table until it refreshes, every hour on the hour. Changes I make here show up in the source pretty much immediately, because they're sent. When I refresh, you'll see the notes did come through, but a couple of things don't. Images don't; the image is gone. And the grid shows up as just a grid. So canvas columns are okay in Cross-doc: if yours hold a lot of images, grids and advanced objects, those won't come through, but if they hold notes, copy and information, they do. Another thing to note: why did this value come through when I didn't refresh? When you make an edit, Coda both sends it and pulls any new values. For example, in the source doc let's change Retail Solutions to 100,000. That won't show up here until the hourly refresh, or until I make an edit. So if I edit this row, Coda sends my change back and pulls the 100,000 through. There we go. Small things to know about how Cross-doc moves information. Cross-doc also lets you delete rows and add rows. If I delete HealthCore here, it deletes HealthCore in the other doc as well. If you don't want that to happen, you can lock the table and allow people to edit values but not delete or add rows. That gives you more control over how your users interact with the data. One more thing. Let's remove locking and look at interactions, a relation column. If you have relation columns in a Cross-doc table, it brings through the display value, but not the related table. If I want the rich data, I can sync that table in too, and then I know that for Green Solutions this was an email and this was a phone call. To have the data about a relation column available, you have to sync it in. We're getting close to done, but there are a couple of key things to know. First, when should you even use this? In our opinion, Cross-doc is primarily for security purposes. If you're okay with everyone seeing the whole pipeline, you should not use Cross-doc to make a closed won table for your account team. It has idiosyncrasies: it only syncs every hour on the hour, changes have to be sent back, and there's extra configuration work. If you're fine with everyone seeing all your data, just make a page in the same doc called Closed Ops, add a view of your opportunities table, and filter it to where the stage is closed won. If you don't need row-level security, do that. Then you don't have to worry about configuration, how much it can sync or how often it syncs. So again, why Cross-doc? Mainly for security. There are other reasons, which we can get into in the comments, but primarily you should think: I'll use Cross-doc when I need to keep a certain subset of my rows private. It also lets you keep columns private. If you didn't want your account team to know the deal value, you'd go to Change what syncs and leave the deal value column out. That gives you better row and column level security, so you're not accidentally exposing data you shouldn't. Lastly, I promised at the beginning I'd get into the advanced mode, so let's do it fast. In Change what syncs, advanced mode lets you connect the sync to a view instead of configuring it here. If I have a view of this table in the source doc, and I call it Closed Ops, I can connect my sync to it. Whatever columns are visible and whatever filters are applied to that view will be reflected in my other doc. It may not show up right away, so let's refresh: options, see all options, Cross-doc, Change what syncs, advanced, select view. There we go: a view of the opportunities table. So instead of configuring it here, I can set it to mirror a view in my other doc. That is Cross-doc at a high level. Believe it or not, there are a lot more small things to know about it, including not just how Cross-doc tables work but also the Cross-doc building blocks: adding, modifying and deleting rows, pushing buttons, and updating pages. If you have any other questions about tables or those buttons and actions, let us know in the comments and we'll see if we can tackle those as well. --- Source: https://simpladocs.com/resources/zz-skill-test-cross-doc-delete-me # The Coda MCP starter kit > Your team copies the same table between docs because the doc boundary says they have to, not because the data changed. **For:** Ops leads connecting Coda docs without a developer **Format:** coda-doc ## What you'll be able to do - Set permission boundaries before an agent can do more than you intended - Skip the connector-per-pair work that never finishes - Start from the three prompts that do most of the actual work ## What's inside - A Coda doc structured for MCP access, ready to copy - The permission boundaries we set on client engagements - Three prompts, annotated with why each is shaped that way - The two failure modes we hit first, and how to avoid them ## Questions ### Do I need to be on a paid Coda plan? The doc structure works on any plan. Some of the automation examples need a plan that allows automations, and the kit notes which ones. ### Is this specific to Coda, or does it apply to Superhuman Docs? Both — they are the same product. Anything naming Coda applies unchanged. ### How much of this needs a developer? None of the doc structure or the prompts. The permission boundaries are configuration, not code. ## Transcript If you have ever copied a table out of one Coda doc and pasted it into another, you already understand the problem this solves. The data is the same data. The doc boundary is the only reason it needs moving. MCP is a way for tools to talk to each other without a human in between. In Coda terms: one doc can ask another for what it needs, get a structured answer, and act on it — without an export, a paste, or a reconciliation step afterwards. The thing worth understanding first is that this is not an integration in the usual sense. You are not wiring doc A to doc B and maintaining that wire. You are giving an agent the ability to read and write across both, and describing what it is allowed to do. Which means the work shifts. Less time building connectors, more time deciding what the rules are. That is a better problem to have, but it is a different one, and teams that skip that decision end up with an agent that can do more than anyone intended. The starter kit has the doc structure, the permission boundaries we use with clients, and the three prompts that do most of the work. Start with the permission boundaries — they are the part people regret skipping. --- Source: https://simpladocs.com/resources/coda-mcp-starter-kit # Coda is now Superhuman Docs: what changes for you (and what doesn't) > Coda is now Superhuman Docs. No migration needed — here's what actually changes: AI Pages, the Docs MCP, million-row databases, and what to do now. Author: [Scott Weir](/team/scott-weir) Published: 2026-07-17 Last updated: 2026-07-27 Tags: Product Updates, Superhuman Docs, Coda, AI Pages, MCP, Databases **Superhuman Docs is the new name for Coda.** As of July 8, 2026, your existing Coda docs, Packs, automations, and pricing all carry over unchanged, **there is no migration needed to do today.** Even if it looks drastic, the name is the least important part of the news... The bigger change is what ships with it. You get vibecoding inside of Superhuman docs, AI that can use your Coda docs both inside of Coda and from your typical AI apps like Claude, ChatGPT, etc, and... finally the potential to store up to a million rows in Coda with the early alpha of Superhuman Databases! Let me tell you everything about it! We've run Simpladocs, our own company, on Coda since the early private beta and implemented it for [200+ companies](/work), and after all I'm [The Coda Guy](https://www.youtube.com/@thecodaguy)... but I wanted to get the news from the Superhuman team directly so we sat down live with two of the people actually building this: **Jeremy** **Olson**, the product lead behind AI Pages (Coda's vibecoding equivalent), and **Bharat** **Batra**, the PM for AI and the MCP; and asked the hard questions that really matters for people that used Coda to run vital workflows in their companies every day: what actually changes for us, and what doesn't with this new Superhuman Docs launch? Here's our honest version. ## The short version - **Coda is now Superhuman Docs.** Same product, new name and exciting new capabilities. [Read the official announcement.](https://help.superhuman.com/hc/en-us/articles/46210093285773-What-s-changing-Coda-becomes-Superhuman-Docs) - **Nothing you need to do and nothing will break.** No migration, retraining or data-loss risk; formulas, Packs, [automations](/blog/coda-automations-basics), and pricing all still work. - **AI Pages & Views** (currently in closed beta). Once released it'll give you the power of "vibe coding" inside of Coda's reliable world. This has us all very excited by the future possibilities in Coda. - **The new MCP** lets AI tools like Claude and ChatGPT interact with your docs and even create native-looking docs with custom formulas for you, all by just chatting with your preferred AI tool. - **Databases** (closed early alpha) will finally blow past today's ~25,000-row limit and reach target up to 1M rows. - **Pricing hasn't changed** as of July 2026, though Superhuman already offers bundled pricing across its tools. ## Why did Coda change its name? Short answer: Coda is now part of Superhuman, so the product needed to fit the rest of the Superhuman ecosystem. Here's the timeline, because it explains everything that follows: - **Late 2024** — Grammarly, the OG writing assistant, acquired Coda. - **Mid-2025** — Grammarly was still in its acquisition spree and bought the famous email app Superhuman. - **October 2025** — [The whole company was renamed Superhuman](https://www.grammarly.com/blog/company/announcing-company-rebrand-to-superhuman/), folding Coda, Superhuman Mail, Grammarly into one AI-native productivity suite and setting the ground for launching a new suite of AI agents called Superhuman Go - **July 8, 2026** — [Coda became Superhuman Docs](https://help.coda.io/hc/en-us/articles/40685056076685-What-s-changing-Grammarly-becomes-Superhuman): new name, new look, and the new capabilities we mentioned; but the same powerful flexibility to build a doc as powerful as an app. So "Superhuman Docs" is Coda taking its place inside a bigger AI suite. So your workflows and all the docs you've built aren't at risk, they'll actually become way more powerful. The main change is the name and the URL domain; that's also why you'll start seeing "superhuman.com" where "coda.io" used to be and all your coda.io saved bookmarks will redirect automatically to the new name (if you're a big enterprise user, this is very relevant to you and we'll explain later how to deal with strict IT security protocols if the change blocked you out of your docs). ## What are AI Pages and AI Views? This is the change that really excites us! **AI Pages and AI Views let you describe the tool you want and have Superhuman Docs build it on top of your existing tables and inside your familiar Superhuman docs interface, it's like vibecoding but WAY better and safer**. Also, you'll no longer need to build buttons and formulas yourself, Superhuman will do it for you. In our webinar we watched a plain table become a vacation-planning board, a drag-and-drop seating chart, and a "World Cup viewing party" dashboard, each generated from a sentence. And the amazing thing is that the interfaces were not constrained by the typical Coda pages, tables and views. With AI Pages you'll be able to build custom interfaces, bespoke coloring, and all the types of elements that you can normally build with Claude and ChatGPT-created apps. **These aren't throwaway mockups.** Every view is backed by your normal tables, and it's collaborative by default — the table stays the source of truth, so edits show up for everyone live, exactly like a doc does today. You can also keep editing by chatting ("make it look like it's from the '80s") instead of hunting through settings. And the good news that IT and security-minded people would love hearing is that this allows users the flexibility to create apps but inside of Superhuman's already polished "garden", so sensitive data stays inside your Coda organization, no risk of installing malicious tools or leaking vital information that could give us nightmares (like the ones we frequently see online because of AI-related data leaks). Why build this? In Jeremy's framing, Coda's building blocks were powerful but capped, and using them well meant understanding schema, formulas, and buttons. The rise of AI removes that barrier. **You no longer need to know formulas to build the tool you need, and the tools you can build got more capable, not less.** So you can build those advanced docs that I've shown you in my [Coda Guy YouTube channel](https://www.youtube.com/@thecodaguy), but without the learning curve to write all the formulas and buttons yourself. It's intentionally sandboxed. The AI can't pull arbitrary code off the internet or make unrestricted calls to other apps that could leak data or execute unintended deletions; external connections run through the familiar Packs, which have already been tried and tested by thousands of users. That's a deliberate trade. You lose a little of the "anything goes" of raw vibe-coding tools, and gain something you can share safely. Sharing an AI View, Jeremy noted, is "just as secure as sharing a Coda doc." *Note: As of July 2026, AI Pages and Views are in closed beta,* with broad access targeted for summer 2026 — a target, the team was clear, not a promise. [Sign up in my newsletter](https://simpladocs.kit.com/superhuman-docs) so you're the first to know as soon as it goes in beta or live. I'll definitely host another webinar then to share new information as soon as we get new clues. ## What is the Docs MCP? The second big change is the **Docs MCP**. If you've been online in the past 6 months, you've definitely seen the term when talking about AI but if it's still confusing, take Bharat's analogy: **an MCP is a universal connector**, like a USB stick, that allows you to plug a SaaS app into whatever AI tool you use (Claude, ChatGPT, Cursor), and your AI chats and agents will be able to read, write and use your Superhuman Docs for you. In practice, we can tell Claude "create a doc, add these tables, write these formulas" and it happens — in Coda, without you typing and using your mouse to do it manually. For advanced users and Coda-geeks, there's one small but really useful new capability. You now get **access to comments**, which the old formulas and Coda's API couldn't reach before. Imagine scanning a meeting Coda doc for unaddressed comments from your colleagues and turning them into tasks automatically. Before the MCP this wasn't possible and comments were often lost in the depths of a Coda doc. Here's where we put our own money where our mouth is. [Our team of Superhuman Docs experts at Simpladocs](/coda-consultants) uses the MCP every single day to speed up our day to day, build amazing docs and help companies solve their bottlenecks with Coda; but we're often guessing what can the MCP do and what's still not possible. Enter... the MCP Capability Matrix. We built a Simpladocs workflow that runs every Monday, uses the MCP to re-test every "no" in the previous list of capabilities and alerts us if Bharat's dev team has released any exciting new capabilities. Sometimes we catch them even before they're announced in public... sorry Bharat. The MCP still has a ton of room to grow. Bharat named buttons-in-tables, automations, full image control, and Packs as the priorities, with most expected over the next two to four months — paced deliberately, because adding tools too fast starts to confuse the AI models themselves... let alone us the users. ## Docs AI vs. Superhuman Go: what's the difference? **Docs AI** is kind of similar to the MCP but with one major difference, it brings all the AI capabilities *inside* the doc. Now you'll find a Superhuman AI assistant that summarizes, creates tables and columns, and writes or debugs formulas without leaving Coda. (Some enterprises turn it off for security, so you may not see it.) With our Simpladocs clients we use it mostly for fast data management and giving newer team members a formula head-start — though, in full transparency, it sometimes still writes formulas we end up reworking because they're not yet fully optimized, but we're convinced the team will keep improving it. The bigger picture is **Superhuman Go**. Today they're two agents: Go works across your connected tools and the web; Docs AI goes deep inside a single doc. Where it's heading, in Bharat's words: "Go can do everything Docs AI can, and Docs AI can do everything Go can." That means you can pull Jira (or any connected source) into a doc, or spin up a custom Go agent (a bug-triage agent, say) that runs directly inside it. We'll talk more about Superhuman Go agents in another blog post. ## Databases: from ~25,000 rows to a million If your Coda tables crawl once they pass 20,000–25,000 rows, this section is for you. **Superhuman Docs is adding databases that target up to... one million rows** without that slowdown. If you're like us, we've had to build workarounds for tons of companies using Coda to circumvent this limitation but it seems that, once Databases are released, that will be a thing of the past... finally! *As of July 2026 this is in closed alpha.* Whether the million-row limit is hard or soft, and what the trade-offs are (you likely won't be able to write as many heavy recursive formulas against that much data), **we genuinely can't tell you yet.** But of everything announced, this is the change we're most excited about, because it removes a real, felt constraint rather than adding a new toy. We'll have early alpha access to this and help the Superhuman team shape it so it helps us Coda builders the most, but we'll keep you in the loop as soon as we can share more information about this. ## The quieter upgrades Among these major topics, the Superhuman team added even more goodies and we couldn't ignore them. So here are some other exciting news that came along with the Superhuman Docs rebranding: - **Table pages** — a full-screen, uncluttered way to work with data-heavy tables. Our hunch (and it's only a hunch) is they're the on-ramp to databases, which is why you can't convert one back to a canvas page. - **macOS desktop app** — tabbed docs and the long-requested **multi-account support** (work and personal, no more incognito windows). Windows version is coming soon. - **Workspace subfolders** — real organization for large enterprises drowning in docs. Closed beta. This will be really useful for doc-sharing permissions and avoiding accidentally giving someone access to an unintended doc, just because you shared the whole folder. ## Do you need to migrate from Coda? (No — here's what to check) For most people, **nothing breaks.** - **No migration required.** On a standard plan, you're good to go. Enterprises with strict security may need IT to whitelist new superhuman.com domains, because the browser automatically redirects your coda.io URLs to the new domain and sometimes IT teams have to whitelist domains. If this is the case, please notify your IT admin team and they'll know what to do. - **Pricing hasn't changed** as of July 2026. That said, Superhuman is moving toward bundled pricing across Go, Grammarly, Mail, and Docs, and AI broadly is trending to usage-based models, so expect changes eventually. We're not privy to specifics; when they're announced, we'll pass them on. - **Your Packs and automations keep working.** One of ours broke because it looked for URLs containing "coda" that now read "superhuman" but it was just a one-line fix. If you've done custom API work, spot-check it; otherwise expect a seamless redirect. In case you've built Coda packs and need help converting them to Superhuman packs, just let me know and [my Simpladocs team will help you](/contact). - **No new or deprecated formulas** to relearn. Our good old [Coda Formula Language](/blog/coda-filter-formula-tutorial) stays the same, at least in spirit since we should now call it Superhuman Docs Formula Language... Our honest read: this is the most significant shift Coda has made in years, and the direction we're going is right. Coda Docs that behave like apps, AI that can actually operate your systems and support for bigger data sets is definitely what Coda was needing. Most headline features are still in beta, so the smart move today is to understand what's coming and imagine where it fits, not to overhaul anything. What's the one workflow in your business that would change most if your docs could build themselves into apps? That's the question we'd start with to prepare for the release of Superhuman AI Pages. ## Frequently asked questions **Is Coda shutting down?** No. Coda is being renamed Superhuman Docs, not discontinued. Existing docs keep working, and no formulas were added or deprecated in the change. **Do I need to migrate from Coda to Superhuman Docs?** No migration is required on standard plans. Enterprise teams with strict security policies may need IT to whitelist new superhuman.com domains. **Will my Coda Packs and automations still work?** Yes. Anything that hard-codes URLs containing "coda" may need a one-line update to "superhuman" — one of our own Packs needed exactly that fix. Custom API integrations are worth a spot-check; everything else redirects seamlessly. **Is Coda's pricing changing?** Not as of July 2026. Superhuman has signaled a move toward bundled pricing across Go, Grammarly, Mail, and Docs; specifics haven't been announced. **What are AI Pages and AI Views?** A closed-beta feature that builds interactive, app-like views on top of your existing tables from a plain-language description. The underlying table stays the source of truth, so views are live and collaborative. Broad access is targeted for summer 2026. **What is the Docs MCP?** A connector that lets AI tools like Claude, ChatGPT, and Cursor read and write your Superhuman Docs content directly — including comments, which the old API couldn't reach. **What's the difference between Docs AI and Superhuman Go?** Today, Docs AI works deep inside a single doc; Go works across your connected tools and the web. The stated goal is convergence — each will eventually do what the other can. **How many rows will Superhuman Docs databases support?** Up to one million rows, versus performance degradation around 20,000–25,000 rows today. This is in closed alpha; whether the limit is hard or soft isn't yet confirmed. *Want the full session?* We covered every feature live, with demos and audience Q&A — [watch the recording](/webinar/superhuman-docs-coda-rebranding) or [browse the resource doc](/webinar/superhuman-docs-coda-rebranding) we shared with attendees. *We break down the tools we build on whenever they make a real move. *[*Subscribe*](https://simpladocs.kit.com/superhuman-docs)* and we'll send you the next one first.* --- Source: https://simpladocs.com/blog/coda-is-now-superhuman-docs # Coda Dashboards: Let's Get Insightful > Learn how to create insightful Coda dashboards with dynamic data manipulation, compelling charts, and effective data visualization techniques. Author: Scott Weir Published: 2024-03-12 Last updated: 2026-09-13 Tags: Coda Tutorials ## The Story Behind the Data Creating effective dashboards requires understanding "the narrative within the data." Dashboards provide valuable insights for decision-making across industries. Rather than simply presenting numbers, successful dashboards use tables, formulas, and charts to tell a meaningful story through context and narrative. ## Dynamic Data Manipulation Dashboards function best when they enable action. "Filtering and sorting data is essential to having dynamic dashboards." Coda allows real-time data interaction and multiple visualization perspectives including charts, tables, and cards, enhancing dashboard versatility. ## Crafting Compelling Charts Effective chart creation techniques were demonstrated during the webinar. Leveraging graphs and canvas controls produces visually engaging, informative dashboards. However, Coda charts have a notable learning curve requiring attention to configuration and presentation details. ## Making a Chart View Not all data suits chart visualization. Evaluate whether data types align with specific chart formats before proceeding. The process begins by typing "/chart" in Coda's canvas. ## So Many Choices! Chart customization options include: - **Axis/Values** - Summarize and select data for visualization - **Aggregate Values** - Combine duplicate values into single data points - **Segment By** - Compare data types - **Orientation** - Vertical or horizontal display - **Range** - Exclude outliers via minimum/maximum values - **Vertical Axis Scale** - Linear or logarithmic spacing - **Stacking** - Display similar values together Make sure you have a clear idea of what data you want your chart to visualize. ## More Useful Coda Resources by Simpladocs Join our [30 Days of Coda](https://docs.superhuman.com/form/30-Days-of-Coda_diW3_MgxjHD) initiative and learn daily with free emails delivered directly to your inbox, or enroll in [The Coda School](https://www.codaschool.io/) to take a comprehensive mastery course. --- Source: https://simpladocs.com/blog/coda-dashboards-lets-get-insightful # Workflow Optimization: It's far different from what you think it is > Learn why workflow optimization is more than just automation. Discover the QAO framework to question, analyze, and optimize your business processes effectively. Author: Scott Weir Published: 2023-11-19 Last updated: 2026-02-24 Tags: Workflow Optimization The biggest mistake teams make when improving operations through automation is focusing narrowly on automation without considering the bigger picture called Workflow Optimization. > "So what is workflow optimization? First one must understand what it is *not*. And certainly it is not simple automation." ## What Automation Actually Is Automation has a narrow scope and targets tasks following predictable, repeating patterns where human judgment isn't required -- such as logging newsletter signups or form submissions into systems. It works best for if/then scenarios with predictable outcomes. However, automating faulty or unnecessary workflows wastes time and money without improving business performance. ## Understanding Workflows A workflow consists of standard, repeated task sequences meant to accomplish goals. These can range from company-wide OKR reviews to simple timecard submissions. Workflows: - Repeat regularly within teams or job roles - Contain multiple steps - May vary depending on context The article provides a bug report workflow example showing logging, severity assessment, and action paths. ## Defining Optimization Optimization ensures a process: - Leads to goal completion - Requires minimal human effort and time - Avoids cumbersome, redundant work ## Consequences of Skipping Optimization ### Decreased Employee Satisfaction and Retention Employees' least favorite job aspects typically involve poorly optimized processes. ### Inability to Scale Scaling requires growth without proportional resource increases. Unoptimized processes consume time that could fuel expansion. ### Suboptimal Outputs Manual-heavy, poorly designed processes increase human error risks, potentially causing data loss or critical failures. ## The QAO Framework ### Q: Question Your Assumptions Before optimizing, verify the process is meaningful and impacts your bottom line. If answers aren't clear, consider eliminating the process entirely. ### A: Analyze Workflow Steps Use process-mapping to document each step systematically. Maintain critical examination -- identify meaningless steps for removal. ### O: Optimize Through Four Methods **Filtering** Trim unnecessary tasks and rituals identified during earlier steps. **Automation** Have computers handle manual, predictable work instead of wasting human time. The article describes a SimplaDocs client case: an employee spent 15 hours weekly entering TikTok video metrics into spreadsheets. A 5-hour API integration automation freed 780 annual hours. **Delegation** Some tasks resist automation due to unpredictability, required judgment, or API unavailability. Delegating to employees or hiring specialized staff handles these appropriately. **AI** Large language models aren't true automation but save significant time through: - Code and script development assistance - Research and analysis - Brainstorming support - Content editing - Team collaboration feedback - Code testing and debugging - Customer service chatbots - Data analysis - Document processing - Internal knowledge surfacing - Trend identification in feedback Proper AI integration can save teams hundreds of hours. ## Conclusion What prevents you from pursuing workflow optimization? --- Source: https://simpladocs.com/blog/workflow-optimization-its-far-different-from-what-you-think-it-is # Tables vs. Views: Do you know the difference? > Understand the foundational difference between Tables and Views in Coda. Learn how views create meaningful pages and keep your data organized and up to date. Author: Scott Weir Published: 2023-11-19 Last updated: 2026-02-24 Tags: Coda 101 Basics ## Today's Topic: Tables vs. Views One of the foundational concepts in Coda is understanding the difference between Tables and Views. Without this knowledge, it's hard to use Coda as anything more than a fancy Google Doc, and we definitely want to get past that! Mastering tables and views is the difference between having a Coda doc that people say "I love using this tool at my job!" and "Are you kidding me, another Coda doc I have to use?" Views allow you to create pages like "Completed Tasks" or "Priority Customers" - they allow you to create pages with meaning. Today's newsletter is geared toward Coda beginners, but even if you've been with Coda for a while, take a look at the Other Sweet Facts section for some tips you may not have seen before. ## What is a Table? Tables are Coda's foundational building blocks, and they are a way to store structured information. Tables are organized in rows and columns, but do not get them confused with spreadsheets! They are far different from a Google Sheet or Excel Spreadsheet. Each **row** in a table represents a distinct object, while each **column** represents a distinct characteristic of or information about that object. For example, in the People table, each row represents a single individual while the columns tell us information about those individuals. ## What is a View? A view is like a mirror-image of your table, a way to display that table elsewhere in your document. Any changes you make to the view will be reflected in the original table, and any changes you make the original table will in turn be reflected in the view. The fact that views are all fundamentally connected allows you to have an always up to date source of truth. **Views are important for two main reasons:** 1. A single table is accessible and editable from multiple locations. 2. You can show unique slices of data with unique column setups. Consider a team with a task table where each task is either "Done" or "Incomplete." Rather than having a large, cluttered table where all tasks live in one place, you can make a **View** on a new page that contains *only* the tasks that are "Incomplete." ## Project Table Example Consider a table of projects with multiple columns: - Due Date - Project Owner - Outstanding Tasks - Reflection on Project The *Reflection on Project* column is only applicable once a project has actually been completed. As a doc builder, you can create two views of the projects table and filter them accordingly. **Main Table:** All of the data - where you build the structure from **View 1:** Projects being worked on. Show only rows of incomplete projects with applicable columns. **View 2:** Projects completed. Show only rows of completed projects with applicable columns. ## Other sweet facts - You can have as many views of a table as you want! - No tables or views anywhere within a document can have the same name. - **The original table you created has some special powers and properties.** Store it on a unique page for easy locating. - Next to each table and view name is a small chain-link icon. Clicking it opens a sidebar showing connections and all related views. --- Source: https://simpladocs.com/blog/tables-vs-views-do-you-know-the-difference # Modifying Multiple Select Lists with a Button > Learn how to modify multiple select list values in Coda tables using a button with ListCombine and Filter formulas in this step-by-step tutorial. Author: Scott Weir Published: 2024-03-12 Last updated: 2026-02-24 Tags: Coda Tutorials With all of Coda's power and flexibility comes responsibility to modify multiple select lists within tables efficiently. The formula used in table buttons is straightforward, but the reasoning behind it requires explanation. ## Objective The goal involves modifying column values by pressing a button. Adding predetermined values to multi-select lists presents specific challenges. ## Three-Step Process ### Step 1: Identify Appropriate Column Find a Coda doc containing a table with a multiple select list column. The column type must be "Select list" or "Relation" with "Allow multiple selections" enabled in column options. List items appear as "chips" rather than plain text. ### Step 2: Add Button Column Add a button-type column to the table. In button column options, select "Modify rows" for the On click action, choose your table name for the Table dropdown, and select "This Row" for the Apply to dropdown. ### Step 3: Update Values Formula In the Update Values section, choose the column to modify. Enter the equals symbol followed by this formula: `ListCombine(thisRow.[ColumnName],[ListValueChipToAdd]).Filter([CurrentValue].IsNotBlank())` ## Common Mistakes Avoided - Converting column values to plain text instead of maintaining chip format - Using single list values that override existing column content - Applying `ListCombine()` without `Filter()`, creating literal "Blank" values --- Source: https://simpladocs.com/blog/modifying-multiple-select-lists-with-a-button # Send Gmail messages with attachments from Coda > Learn how to send Gmail messages with attachments directly from Coda using Google Apps Script. Step-by-step guide with code and button configuration. Author: Scott Weir Published: 2023-08-11 Last updated: 2026-02-24 Tags: Coda Integrations Packs, Coda's word for integrations with other services, allow Coda to truly become the all-in-one doc. Bringing your teams work from all over the internet into one unified space. The Gmail pack for Coda, one of the most popular packs, is lacking one major feature though: > The Gmail pack for Coda cannot send email messages containing attachments While the Gmail pack may not be able to send emails with attachments, that does not mean that Coda cannot do it. The guide below will demonstrate how to use Apps Script, a Google providing coding environment, to easily send emails with attachments using a button in Coda. Apps Script does require the use of a little bit of code, but I promise you can do it. Yes you - Although you have never written a line of code before, you *can* do this. ## Step 1: Create an Apps Script project The first step is setting up a new Apps-Script. You can do this by: - Going to script.google.com - Typing script.new into your browser Once you have navigated to Google Apps-Script you are going need to start a new project. ## Step 2: Set up your Apps Script Now its time to actually get our code in our project, and set it up so its ready to connect to your Coda doc. ### Copy/Paste Code Copy and paste the provided code into your Apps Script project. The code contains three functions: `replaceSpace`, `sendPdfEmail`, and `doPost`. ### Get ready to connect to Coda You will have to do three quick things: 1. Save the project 2. Run the project to authorize it 3. Deploy the project as an application Next, you will need to RUN the project in order to authorize it. Authorizing it is similar to inputting a username and password - you are telling the Apps Script that it is ok to send emails on your behalf. Once you press Run you will be walked through the normal flow of signing in/logging in with your gmail account. In order to deploy your script as a web app, follow these steps: 1. Press the big blue DEPLOY button in the top right corner of your screen 2. Choose "New Deployment" 3. Select the "Web App" deployment type using the small cog wheel in the top left of the pop-up window 4. Change the "Who has access" to be "Anyone" 5. Press Deploy! 6. Once deployed, it will give you both a deployment ID and a URL. You want to copy the URL specifically and save it for the next step ## Step 3: Set up Coda to send emails! You did it! You now have a script running that will accept inputs from a Coda doc and send Gmail messages with attachments. Now we just have to connect our Coda doc to your apps script and set up the actual button that will do all the magic. You've only got a couple steps left and then you are done: 1. Install the Apps Script pack into the Coda doc you want to send messages from 2. Configure the button to send messages 3. Send your first email! ### Install the Apps Script Pack There is a free pack in the Coda gallery called "Apps Script" - and you can install it in any Coda doc by doing the following: Inside a Coda doc: - Insert > Packs > Search "Apps Script" > Add to doc for free The Apps Script pack is going to have a button that allows us to trigger or send information from a Coda doc directly to your apps-script project you created in the previous step. ### Configure a button to send your email Sending emails from a button is best done from a table. If you need to learn more about sending emails from Coda in general, check out the resource that runs you through best practices. Likely, if you have a table to send emails it will look like the following with common column types of name, email, subject, attachment, name of attachment, etc. But honestly, you can set up the table however your workflow demands. Once you have your table, create a new button column, and choose a pack action, and choose the Apps Script pack and then choose the "Trigger web app" action. Once you have your button in your table its time to configure, or set it up. You will need to input the following things into your button: 1. The Web App URL you copied from Step 2 of this guide 2. Method: Type the word "POST" into this box 3. Body: This is going to be a formula input - use the JsonBody() formula from the Apps Script pack. For the Body part of the button, this is where you will define what information *from* your Coda doc gets sent out to the apps-script, and then eventually in the email. The parts that need to be exact are the words: - to - subject - body - url - pdfName And then the *value* or the argument directly after the "url" portion needs to be the `Attachment.First()._merge().ParseJSON("publicUrl")` formula. All the other green chips will be unique to your document or table. And thats it! Now you can start sending emails with attachments from any Coda doc. ## A little more about this workflow This workflow is just one way that Coda docs can be extended using Apps Script. SimplaDocs has built dozens of Apps scripts for clients that connect to their Coda docs in a myriad of ways automating all sorts of business processes. While apps script can be used for any sort of automations, it is especially helpful for automations or integrations with Google based services. Don't hesitate to contact us if you need any help! --- Source: https://simpladocs.com/blog/gmail-with-attachments # Coda Forms 101: Everything you need to know to use Coda Forms > Everything you need to know about Coda Forms: why to use them, how to build and publish them, and tips for customizing layout and design for better UX. Author: Scott Weir Published: 2023-09-25 Last updated: 2026-09-01 Tags: Coda 101 Basics Series ## Why use Coda.io to make forms? The answer is simple: the flexibility and control you have with the data that gets submitted. Most dedicated form providers require that you export, download, or transfer the information to actually use it. But if your information is in Coda, you can use it intentionally RIGHT IN CODA. For example: - Need a sign up form to gather names and emails? Make a form, get the info, and send the newsletter using a pack right from your Coda doc. - Want to collect customer reviews? Make a form, get the info, and analyze the rating or testimonial with tools right in Coda (including AI!). - Have to get customers to submit bug reports? Make a form, get the info, and get notified of their needs right from your doc. Seeing a pattern? Simplicity. Forms in Coda are also easy to create because they're just a view of a table. You can start by creating either the table or the form and after a few clicks to show or hide columns and publish the form, you're on your way to collecting data. ## Downsides of Coda forms There are a few cons to using Coda forms. 1. If you need some major conditional logic when creating forms, Coda is going to struggle. Small tweaks are certainly possible with a bit of formula wizardry, but big conditional logic requirements are going to be better in a different, stand-alone form tool. 2. There's less UI/UX control with Coda than dedicated form makers. Here again, however, formula knowledge can come in handy if you want to change some colors, but if you want something to really blend in or match with your branding, it's going to be tricky getting it there. 3. Finally, there's no option to redirect to a different link after the user submits their response. For the typical user, these downsides aren't going to outweigh the benefits of using Coda for forms, but if you're a power form user and want help making Coda's forms work for you, please contact me! ## Build a Coda form with me! Ok, let's build a Coda form. First, make sure you're signed up for Coda. If you don't have an account yet, click here to get one. There are two ways to create a form in Coda: from an existing table or as a brand new table. ### Starting from an existing table Let's say you have a list of team members already built showing varying days of availability for a team meeting. In just a few clicks, you can turn this into a form to collect info directly in Coda. Hover on the table, click *Options*, click *...*, then choose *Form*. Presto change-o, you've got a form! The current and any new responses will live in the table view with which you started. ### Building it as a new table Everything in Coda starts with a / (forward slash). In your doc, simply type */table*, and follow the steps above. Or you can type */form*, and edit the fields in the form view. In the latter case, creating the form view directly also creates the connected table in which the results will populate. As you edit the column names and types, the form view will automatically update, and vice versa. ## How to publish a Coda form? There are two main ways to use Coda forms. If your users all have Coda accounts, you can create a view of the form in the doc and allow them to fill out the options from there. But the most common way you'll probably use a Coda form is to publish it so someone who doesn't have an account can respond. Hover on your form, click *Publish form*, and then choose *Create link*. From here, you can *Preview form* to check it over, *Copy link* to send it, and even add some *Privacy* options. *Allow submissions* is toggled on by default. It MUST be on to collect data from users. The other options here are more advanced - stay tuned on how to use them! Now with your published form link you can share it to an email list, embed it on your website or even in a different Coda doc! Basically, share it however you would normally share a link to a form! ## Editing form layout and options Right now, your form is certainly usable, but it probably looks a bit ugly, right? Let's fix that. Hover on the form view and click *Edit layout*. There are many options for customizing your Coda form from here. The first is that you will want to add a title (otherwise it will display to the user as "Untitled Form"). Everything after that is purely optional but can really enhance the UX/UI of your form: - Add a title - Add a cover image by uploading a branded image, or something from Unsplash - Add a form description - Show/Hide columns for the form view (they can still be visible in your table view) - Choose questions that are required (indicated by a red *) - Add a question prompt (without changing the column name) - Add question instructions - Edit the layout by hovering over the question, click + hold, and drag it to where you'd like it to be, including into columns - Change question style (select lists, for example, can be radio buttons / checkboxes or drop downs) - Edit the form submission message - Show/Hide Coda branding ## Video tutorial step by step If you'd like to see how this all comes together step-by-step, check out [the YouTube video tutorial](https://www.youtube.com/watch?v=eXJ8bfo_udQ)! Now that you've got a handle on the basics of making a form in Coda, you may be interested to go a bit more in-depth. If you have questions, we'd love to hear from you - reach out or check some of our other resources below. --- Source: https://simpladocs.com/blog/coda-forms-101-tutorial # Master Coda's Filter Formula > Learn how to master Coda's Filter formula for tables, views, and dashboards. From basic filter bars to advanced Filter() formulas with practical examples. Author: Scott Weir Published: 2023-07-20 Last updated: 2026-09-13 Tags: Coda 101 Tutorials ## What does Filter even mean? Filtering a table or view is comparable to "looking at a restaurant menu and deciding you actually only want dessert so you flip to the back and focus on those items." In Coda, users request: "take this table and only show me the items that match a certain set of criteria." The example table contains information about people's ages and heights. ## Anyone can filter using the Filter Bar Coda offers a user-friendly filtering option. Users can click "Options" > "Filter" when hovering over a table. Toggling "Enable filter bar" allows anyone to filter without changing others' views. Users can select which columns are filterable. ## You choose the filter for someone else Users can create pre-filtered views for specific audiences. This prevents the need for constant manual filtering when recipients only need particular information subsets. ## Coda's Filter() formula The Filter() formula enables advanced functionality including table connections, dashboard creation, and data insights. It comprises three main parts: 1. The table to filter 2. Criteria defining which rows to return 3. The desired column (optional) ### Basic Example A simple formula filters the People table: "filter for anyone whose name is 'John.'" ### Intermediate Example A more complex formula states: "look into my Expenses table and find only rows where the month matches this row's month and the year was 2022. Then return the average of those amounts." ## More Resources Users seeking mastery should explore [The Coda School](https://www.codaschool.io/), which teaches data-types, Boolean operators, and list principles in depth. --- Source: https://simpladocs.com/blog/coda-filter-formula-tutorial # Coda Automations Basics > Learn the basics of Coda automations including row changes, time-based triggers, form submissions, and webhooks to eliminate errors and boost efficiency. Author: Scott Weir Published: 2023-07-20 Last updated: 2026-09-13 Tags: Coda 101 Basics Series Automation is the technique by which something becomes automatic - an item, a process, or a system. By setting up automations for predictable and repeatable tasks, you eliminate human errors and improve speed and consistency. ## How to access Coda automations panel? Access the Automations sidebar by clicking the small gear symbol in the upper right-hand menu, then select *Automations*. ## Parts of the Automation The Coda automation formula consists of three parts: 1. **When** - "When something happens in my table..." - This tells Coda what to watch for (row changes, calendar events, form submissions, webhooks). 1. **If (optional)** - "But only if..." or "And also if..." - Conditions placed on the first part to get granular with requests. 1. **Then** - "Do this thing" - What you want Coda to do (press buttons, notify users, send emails, add/delete rows). Template command: *"Hey Coda, when a row is changed in the _____ table in _____ column, but only if it's _____, then you can _____."* Example: *"Hey Coda, when a row is changed in the Tasks table in Complete column, but only if it's checked, then you can notify a user."* ## Coda Automations' Limits Automation commands take time to execute as they travel to Coda's servers and back. They may take 3 seconds to several minutes. Free and Pro plans have monthly automation run limits; Team plans and above have unlimited instances. ## Types of Coda Automations Four pre-configured automation types exist: - Row changed - Time-based - Form submitted - Webhook invoked ### Row Changed Useful for sending notifications, archiving/deleting rows, or creating modification logs. Example: notify users when tasks are marked complete. ### Time-Based Triggered by cadence (hourly, daily, weekly). Great for recurring tasks and reminders. These can filter information using formulas without requiring conditions. ### Form Submitted Triggered each time a form is submitted from your doc or published link. Useful for data population, auto thank-you emails, or notifications. ### Webhook Invoked Triggered by incoming webhooks (connections between applications). Great for notifications, digital product delivery, real-time delivery notifications, and archive systems. ## Video tutorial step by step For webhook setup details, see the YouTube video [*"Coda VS Zapier: Coda's automations may put Zapier out of business"*](https://www.youtube.com/watch?v=ukfO_RwK9gE). --- Source: https://simpladocs.com/blog/coda-automations-basics # Coda AI: 8 Mind-Blowing Things You Can Do > Discover 8 mind-blowing things you can do with Coda AI, from planning trips and editing text to analyzing reviews and drafting emails automatically. Author: Scott Weir Published: 2023-07-19 Last updated: 2026-09-02 Tags: Coda AI Series Coda AI is an incredibly powerful tool that can help you with a variety of tasks. In this blog post, we will showcase eight mind-blowing things that Coda AI can do, from planning a trip around the United States to analyzing customer reviews and drafting emails. The sky's the limit! ## What is Coda's AI Assistant? Artificial Intelligence (A.I. or AI) made a gigantic splash in the tech world in late 2022. Since then, it seems like every platform is incorporating AI into their product. Many are even requiring their users to pay extra for access to their AI. However, once you have a Coda account, you're able to use Coda's AI Assistant! As of the writing of this post, Coda AI is in beta. What's so great about AI? Keep reading for eight things you can do with Coda's AI right now! ## 1. Plan a trip Anyone who has ever planned a trip, let alone one with kids, knows that if we had a magic wand to make it happen, we'd use it in a heartbeat. Now, we can! With Coda's AI you can create a table of any U.S. state (or heck, why not all of them?!), make columns for whatever other details you'd like and have AI fill in the info! Coda AI can even help you make an itinerary for your trip that includes key activities and/or kid-friendly options. ## 2. Editing Existing Text You likely already have pre-written content that you might need to edit and revise. Maybe you're looking for jobs and you need to spruce up your cover letter, or perhaps you're a web copy editor and need to change the tone of some copy. Anything. Really. Instead of spending hours editing everything, have Coda's AI do it for you. Simply select the text you want to edit, and from there prompt Coda AI to revise - you can shorten the text, lengthen it, choose a tone, whatever you can imagine! Don't forget that you can change it using AI to your heart's content. Don't like a certain part of the text? Highlight just that part and ask AI to change it - change your prompt or whatever! ## 3. Fine Tune Content If you want Coda AI to get really granular with your already written content, check out the FREE template, "Editor", on CodaTemplates.io. With the Editor template, you can have Coda's AI fine tune anything by selecting from a variety of settings. ## 4. Summarize Meeting Notes and Send to Slack Let's say you diligently take notes at your weekly team meeting. A colleague is out that day and needs to see a quick run down of what they missed. If you take your notes in Coda already, this is extra easy. Simply have your notes in one column of a table, add another column and add the AI assistant to it. Ask Coda AI to summarize those meeting notes. Remember, you can specify the length of the summary! In another column, add a button for Slack. In the button configuration, you'll have the content be the AI summary of the meeting, and pick which channel to post it to. Using Coda's automations means that you wouldn't even need to push that button if you don't want to! ## 5. Analyzing Customer Reviews Whether you sell a product or service, you're likely collecting customer reviews. Coda AI can help you analyze those reviews and know which customers love your product and which do not. You can use a Coda form to get data from your clientele, or if you have your Shopify account connected with the Coda pack, you can have Coda AI take their comments and get a numeric value for each review. ## 6. Drafting Emails Based on Customer Reviews Once your Coda AI has analyzed the customer reviews, you can use it to draft emails based on how the customer viewed your product. Whether you want to offer them a discount code or tell them about a different product they might be interested in, Coda AI can draft an email for you in just minutes. Again, you can integrate a Coda pack, in this case the Gmail pack, to push a button when you're ready to send that email. ## 7. Using Coda AI as a Writing Assistant Coda AI is an incredible writing assistant that can help you draft emails, blog posts, social media posts, and other content. Give it some ideas of the content you want to draft, tell it the kind of format you want, give it a style like informal or a tone like funny, and Coda AI will start drafting it for you. Once it's been generated you can change the text in any way, or completely refresh the AI Assistant and have it start over. If you want to test this in action, grab the FREE template "AI Drafter" on CodaTemplates.io. ## 8. Auto-Emailer Coda AI can also help you respond to emails. By using the Gmail Pack to pull in all your email messages, you can use AI to decide whether you even need to respond to an email. If you do, Coda AI can draft a response for you, and again, by integrating that Gmail pack, you can get the email to send automatically using a button. ## Video tutorial step by step If you want to see exactly how this was done, check out the video ["8 mindblowing things you to do with Coda AI"](https://www.youtube.com/watch?v=yIPo3MGcaCQ)! As if Coda couldn't get any better, the AI Assistant is seriously EPIC! Let me know in the comments if you've had a chance to try it out in any of your docs! If you have questions, we'd love to hear from you - reach out at [info@simpladocs.com](mailto:info@simpladocs.com) or check out more resources below. --- Source: https://simpladocs.com/blog/coda-ai-8-mind-blowing-things-you-can-do # Leverage Coda Detail Layouts with a Single Button! > Unlock conditional Coda detail layouts with a single button to tailor user views based on roles. Learn how to set up role-based permissions using Coda tables, duplicate views, and a custom button formula to deliver the right detail layout to the right user. Practical step-by-step instructions and real Coda formulas included Author: Scott Weir Published: 2024-04-29 Last updated: 2026-02-24 Tags: Coda, Tutorial, Table Layouts Even if you’re a beginning Coda user, you’re likely well-acquainted with the **Detail layout** (anytime you expand a row to view the details of it). But if you work on a team with users who have different permissions to view data, did you know those layouts can actually be used as a pseudo-permissions management system? Today I’m going to tell you about a bit of a power-user trick to ensure that only people with certain roles can view the detail or edit parts of your data by leveraging detail layouts. It's a bit of a more long-winded post - but if you're into fun Coda tricks this post is for you! *If you're a visual learner instead, I have this whole walkthrough in *[***video***](https://youtu.be/-d17nNdofFs)* as well.* ## Roles Table First, you’re going to need a table that sets the permissions that people have in your doc for detail views. The easiest way to do this is create a table and add the person’s email address and their role in the doc. For the sake of this example, we’ll assume you have some sort of a doc where team members can submit ideas (Submitter), and then someone else approves them (Designer). *Example of a permissions table in Coda. This example is titled "Roles."* ## Main Table and Views From here it gets a bit more complicated, so stick with me! Now you’re going to need the original table of data - all the information about the project, task, whatever. In our situation, we are pretending that we have a task table with two end user groups: 1. **Designers** (People who need to complete design related tasks) 2. **Submitters** (People who submitted design tasks to be completed) Now copy and paste the table and name it “VIEW - Designer”, and paste the table again and name it “VIEW - Submitter.” Now that you have your two new views, you're going to need to go ahead and edit the layouts of those view. This is where you are going to start defining rules around who gets to view or edit what data. If you don't know how to edit layouts of tables, simply click the vertical ellipsis (3 stacked dots) next to a table and choose **Edit layout**. *Click the vertical ellipsis (3 stacked dots) next to a table and choose ****Edit layout****.* ‍ If you only have one layout right now, go ahead and rename it to “Designer” and show or hide the columns you want the Designer roles to see. Once you have that set, you can click the vertical ellipsis in the **Edit layout** and choose “Duplicate.” Rename it to “Submitter” and hide or show any columns you want visible only to the Submitter roles. And once more, “Duplicate” the view and now we’re going to do a bit of a silly trick that I promise will be important later. Name this new view “Default,” and hide every single column. Create a new column and type the following in as a formula (**Calculate** column type), quotations and all: “Please click the Open button to view details about this row.” And then show only this row on your Default view. Feel free to make it big, center it, remove the column label, etc. so that sentence is the thing that stands out. ## Table Layouts Alright! So now you've made three different table/detail layouts for a your tasks table: 1. Designer layout 2. Submitter layout 3. Default layou Now you need to make sure that the table layout views match the table title. For your “VIEW - Designer,” open a row, click the vertical ellipsis, Edit layout, and choose “Designer”. For your “VIEW - Submitter,” open a row, click the vertical ellipsis, Edit layout, and choose “Submitter”. And for the table which users will actually work out of, choose the "Default layout" ## The Button Now let’s make a button that will conditionally show the correct layout to a user depending on their assigned "role". I like to name the column “Open.” (I know, so descriptive.) In the button settings, you’re going to type the following formula: *Formula to type in the button settings: If(Roles.Filter(User().Email=email of person).Role.First()=Designer,OpenRow(thisRow, viewOrLayout: VIEW - Designer),OpenRow(thisRow,viewOrLayout: VIEW submitter)* ‍ Basically you’re saying, *“Hey Coda, look at the Roles table and if the person who is using this doc’s email is in the table, look at their assigned role. If they’re a Designer, show them the Designer layout view when they click this button. Otherwise, show them the Submitter layout view when they click this button.”* ## The Silly Part Now you might be wondering, “Hey Scott, what if a person doesn’t click the Open button to see something and they just try to expand the row?” Well, this is where that silly little “Default” layout text you made comes into play. On your main table, open a row, click the vertical ellipsis, Edit layout, and choose “Default”. Now if someone tries to expand the row, the Default view is that text prompting them to use your button! You’re all set to leverage the power of detail layouts in your doc! Will this be part of your Coda workflow? ## More Useful Coda Resources by Simpladocs Enjoyed learning more about Coda with this post and want to learn more? From Coda lover to Coda lover, we've selected some other interesting and useful resources we think you'll love. Check them below👇 - ​[**Access Tables: Limit access to sensitive data in a Coda Doc**](https://youtu.be/aft9wHI0zfQ) --- Source: https://simpladocs.com/blog/leverage-coda-detail-layouts-with-a-single-button