The tool loop
Describe, request, execute, return: who does each step.
What you’ll learn
Four ideas, one module
Tools are ordinary code
Search, code execution, databases and APIs, run by your app.
Permissions by risk
Read, write, irreversible, never exposed: and the control for each.
MCP without the magic
An open protocol for connecting apps to tools and data.
Applied exercise
Design a travel assistant’s tools
Design the tool surface of a travel assistant and decide which capabilities should never be exposed directly.
- Read tools
- Write tools
- Needs human confirmation
- Never exposed to the model
Cheat sheet
The model only asks. Your code decides what runs, and with whose rights
One page you keep: the questions to ask on every project, the rules of thumb, and a checklist you can use on your own product. All ten come with The Book.
Leave at the door
Five myths this module breaks
| Myth | What’s actually true |
|---|---|
| “The model runs the API call.” | Your application runs it. The model only asks. |
| “With tools, it can reach anything.” | Only the tools you define, within your limits. |
| “A valid call is a correct call.” | Well-formed arguments can still be wrong values. |
| “The prompt says don’t, so it won’t.” | Instructions aren’t permissions. Enforce in code. |
| “MCP makes the model smarter.” | It standardizes connections. The model is unchanged. |
Before you move on
Can you call this one?
A travel assistant booked a hotel the user only asked about.
Name three places this could have gone wrong. Which fix works even if the model errs?
How we would answer
- Model it misread the user’s intent and chose the booking tool.
- Tool design the tool description was vague, or search and book were one tool.
- Context an earlier turn or retrieved note suggested the user wanted to book.
- Permissions the booking tool ran without a confirmation step. This is the fix that holds regardless of the model: the app requires the user to confirm before any booking.
- Evaluation nobody tested which tool gets picked for “asking about” requests. That’s Module 09.
Every module ends on a question like this. Join the waitlist →
The Action Protocolist
Zane Imani
investigates the boundary where AI stops generating words and starts making things happen.
Episode 07 · How models interact with the real world
Included with the course.
Coming soon · an AI character from the show, not a real researcher.
Next · Module 08