Practical guides to putting AI to work.
Choose the guide for your task. Each explains when the approach helps, the steps to take, and how to check the result.
- Library 12 field guides
- Operating route Map / Build / Control
- Receipt Signal → Decision → Proof
Choose the question you need to answer.
- 01 MCP implementation guide
How to connect AI to your business tools with MCP
MCP, the Model Context Protocol, lets an AI assistant use tools and read information from other systems.
- 02 Automation decision guide
How to choose your first AI automation
Start with one task your team repeats.
- 03 Governance operating guide
How to set rules an AI workflow must follow
AI governance means enforceable rules for what a system may read, suggest, change, or send for review.
- 04 Approval design guide
How to give people useful control over AI decisions
Human-in-the-loop AI means a person reviews a defined decision before the work continues.
- 05 Release evidence guide
How to test an AI agent before giving it more access
Test the agent on the work it will actually do.
- 06 Identity and access guide
How to control who can access an MCP connection
An MCP connection lets AI use tools and information.
- 07 Architecture comparison
MCP or an API: which connection does your project need?
An API lets software exchange information or request actions.
- 08 Marketplace operations guide
How to organize Webflow Marketplace reviews
Treat submission, validation, review, approval, publication, and monitoring as separate steps with named owners.
- 09 App review guide
How to prepare a Webflow app for review
Choose the exact app version to submit and test the installation and main user task.
- 10 Template review guide
How AI can help with Webflow template review
Use automation to gather evidence and run repeatable checks.
- 11 Definition guide
How to map a task before choosing AI tools
Follow one business task from what starts it to the result you need.
- 12 Operating evidence guide
How to see what your AI workflow did
Keep a work history that connects technical activity to the business task.
Read for a decision. Leave with a system your team can run.
Each guide moves through the same four-part operating route, so the reader knows what to observe, protect, keep, and prove.
Start with the task you want to improve.
Choose a task that causes delays, repeated work, or review problems. Use that task to decide which guide to read.
- live handoff
- named owner
- observed delay or rework
Set the fit, pause, and approval conditions.
Each guide marks where AI can assist, where a person decides, which permissions matter, and what should stop before a tool path is selected.
Follow the steps and keep the results.
Record the inputs, steps, approvals, results, and recovery instructions. Keep them when you change tools or AI models.
- workflow map
- runbook
- decision rules
- recovery path
Follow every claim back to proof.
The guide ends with a receipt: the source, rule, decision, result, and evidence that lets the next operator understand what happened.
Before you choose a guide
What is an AI workflow system?
An AI workflow system connects tools to carry out a business task. Its rules define what AI may do, who approves the work, and how to check the result.
Where should a team begin with AI workflow automation?
Begin with one repeated handoff that has accessible source records, a responsible owner, measurable delay or rework, and reversible actions. Map it before selecting models, connectors, or agent frameworks.
Why does this library include MCP and Webflow operations?
MCP guides explain the connectivity and authority layer. Webflow operations guides show those principles inside real review, app, template, and Marketplace boundaries where evidence and human judgment must remain distinct.
Choose the live handoff behind the guide.
The library helps you recognize the pattern. The private draft turns one real workflow into an owner, boundary, operating route, and first proof requirement.
- Owner
- Your workflow operator
- Authority
- Draft the workflow; no production mutation
- Proof
- Private map with owner, decision, stop, and receipt
- State
- draft
- 01 / Guide Choose the closest operating pattern.
Use the fit and pause conditions to name the right starting point.
- 02 / Map Bring one live handoff.
Name the source, owner, action, approval boundary, and failure state.
- 03 / Proof Set the first verification gate.
Decide what must be visible before any build or production change.