Module 05 / 08
Agents & Tools
Move from single model calls to systems that use tools, plan work, and handle failure.
The point
Agents are useful when work requires decisions, tools, feedback, and multiple steps. They also fail in new ways.
Start with
Read next
Understanding check
You should be able to…
- choose workflow vs agent intentionally
- design tools with inputs and outputs the model can use
- handle uncertainty, retries, and partial failure
- measure whether the agent is getting more reliable
Practice with an agent
Give one agent one reliable tool
beginner · codex or claude, starter repository, typed script
Make
one typed tool with a narrow purpose, inspectable output, and an explicit failure result
You know it works when
the agent uses the tool correctly on five cases and stops or asks for help on the seeded failure
Go deeper by building
Build a GitHub issue triage agent
intermediate · typescript, github api, model API, structured outputs
Make
an agent that reads an issue, labels it, asks clarifying questions, and drafts a fix plan
You know it works when
run it on ten issues and record correct labels, bad labels, and failure reasons