Skip to content
Skip to the lesson
← RoadmapDay 77 of 90Agents & Prod AI2h 20m

Tool calling: letting a model call your functions

By the end of today you can give a model a set of functions, understand exactly what it does and does not do when it picks one, and explain why the model never executes anything itself.

YesterdayOn Day 71 you made the model return data matching a schema. A tool call is that, plus a name.

TomorrowTomorrow you harden the boundary: validating what the model asked for before you run it.

01

Why this matters

Tool calling is the mechanism behind every agent, every MCP server, and every AI feature that does something rather than saying something. It is much simpler than it sounds, and understanding it plainly demystifies the rest of the phase.

  • Tool calling
  • Tool definitions
  • The tool exchange
  • Who executes what
02

Learn it

70 min

Copy this into Claude or ChatGPT. It quizzes you before it explains anything, which is deliberate. The resources under it are how you check what it told you.

Today's Master Prompt

Free · sign in

A prompt written for this day alone: your level, the exact scope, what to leave out, and an instruction to quiz you before it explains anything. Paste it into Claude or ChatGPT and it teaches you today's material.

Sign in to continueNo card, now or later.

Check it against something that is not a model

An assistant can be fluent and wrong, and on a topic you met today you will not catch it. These cover the same ground and were made by people who do this for a living, so they are what you hold the explanation up against. They are other people's work and we only link to them, so judge them for yourself.

3 hand-picked resources

Free · sign in

Videos, official docs and articles covering the same ground, each opened and annotated by hand. They are what you check the assistant against on a day you cannot yet catch it being wrong.

Sign in to continueNo card, now or later.
03

Build it

45 min

Build a working tool-calling example with two tools of your own. Print the complete message array after every step so you can see exactly what the model returned and what you appended. Then rewrite one tool's description to be vague and confirm the model stops selecting it correctly.

04

Recall it

25 min

Answer out loud, reveal, then mark honestly whether you had it. That score is the only thing on this page you do not get to choose.

5 recall questions

Free · sign in

Questions you answer from memory, then grade yourself against the real answer. The score is carried into the mastery rating below it, so an honest miss cannot quietly become a tick.

Sign in to continueNo card, now or later.
05

Rate it

Completion and mastery are tracked separately. Be honest, because an inflated rating only means the concept resurfaces sooner.

Mastery tracking

Free · sign in

Rate yourself against five named criteria per concept. Completion and mastery are tracked separately, and anything you rate shakily comes back automatically on a spaced schedule.

Sign in to continueNo card, now or later.
06

Recap

  • 01The model requests; your code executes. It never runs anything itself
  • 02The description is the entire basis for the model's choice
  • 03Every tool call adds messages that are re-sent on every later turn
  • 04One exchange is tool calling; a loop around it is an agent

Your progress

Free · sign in

Mark days complete, pick up where you left off across devices, and watch completion and mastery diverge. Free, and the account exists only so ninety days of work cannot vanish with a cleared browser.

Sign in to continueNo card, now or later.