- Home
- Guides and documents
- Building Effective Agents Cookbook
Building Effective Agents Cookbook
Minimal notebooks for the common agent workflow patterns
What it is
Reference implementations that accompany Anthropic's Building Effective Agents article. Notebooks walk through prompt chaining, routing, parallelisation, orchestrator-workers and evaluator-optimizer loops, plus newer ones on async multi-agent orchestration and agent teams under latency budgets. Useful for anyone deciding how much agent structure a task needs.
Good for
- Study prompt chaining and routing in code
- Prototype an orchestrator-workers flow
- Add an evaluator-optimizer loop
What you need
Claude API key; Python and Jupyter
Sources
- https://github.com/anthropics/claude-cookbooks/tree/main/patterns/agents (project README, read 11 Nov 2026)
- https://api.github.com/repos/anthropics/claude-cookbooks (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.