Course catalog
Give the model hands — tools, loops, and guardrails.
An agent is what turns a chatbot into something that can actually do things. The durable idea behind every framework is small: a loop where the model reasons, your code runs a tool, and the result feeds back until the job is done. You'll build that reason-act-observe loop in Python, wrap plain functions as tools with JSON schemas, let the model choose among several tools, and give the agent memory and multi-step plans. Then you'll make it safe: approval gates before dangerous actions, guardrails and stopping conditions, and — just as important — knowing when a plain function beats an agent.
Section 1
What an agent is and the loop it runs.
Section 2
Describe tools, call them, feed results back.
Ship a secure TypeScript app built with AI in your workflow: tested algorithms, tools kept inside safe limits, architecture choices you can explain, and releases you can check after they go out.
16 course sequence
Build and run a real AI product: it searches your own content, uses only the tools you approved, is tested the same way every time, has a plan for when it fails, and shows its speed and cost.
11 course sequence
Eligible first-time members can get 7 free days · Cancel anytime
Get startedSection 3
State, scratchpads, plans, and stopping.
Section 4
Gates, guardrails, and when not to use an agent.