AI Agents with Tool Use
Build agents that call your functions, loop until the job is done, and stay inside the guardrails you set.
What you'll be able to do
- Define tools with JSON schemas
- Write the agent loop (and know when an SDK runner is enough)
- Add approval gates for risky actions
- Log, trace and evaluate agent runs
The curriculum
4 modules · 11 lessons · 139 minutes
Module 1When to build an agent2 lessons
- Single call, workflow or agent?Free preview10 min
- Tool use explainedFree preview12 min
Module 2Your first agent3 lessons
- Defining tools12 min
- The loop14 min
- Parallel tool calls9 min
Module 3Guardrails3 lessons
- Human approval steps10 min
- Budgets and stop conditions9 min
- Prompt injection basics12 min
Module 4Production3 lessons
- Tracing and logging11 min
- Evals for agents14 min
- Project: a research agent26 min
Who it's for
Developers ready to go beyond single prompts.
Requirements
- •Python or TypeScript
- •Comfort with HTTP APIs
Start now with free tutorials
Free guides on the same topic, available to read today.
Build with LLM APIs.
Your first Claude API call in TypeScript and Python
Install the SDK, make a request, stream the answer and cut costs with prompt caching, in about ten minutes.
Build with LLM APIs.
RAG in plain English (and a minimal implementation)
How retrieval-augmented generation lets an LLM answer from your documents, and the smallest version you can build today.
You might also like
Chat with your docs.
Build a RAG Chatbot on Your Own Documents
Ship a chatbot that answers from your PDFs and docs, with citations, using embeddings, a vector store and an LLM API.
Prompts that land.
Prompt Engineering Masterclass
Go from vague questions to reliable, structured prompts that work across ChatGPT, Claude and Gemini.
Zero to shipped.
Claude Code from Zero to Shipping
Use an AI agent in your terminal to plan, write, test and ship real features, without losing control of your codebase.