Workflows · Skill

Building effective agents examples

Anthropic’s orchestrator-workers notebook demonstrates model-driven task decomposition and execution by specialist prompts.

+ Follow

Builder facts

  • Task decomposition. An orchestrator emits an analysis and XML subtasks, each with a type and a description selected at runtime. Source ↗
  • Worker calls. The Python example calls each worker sequentially with the original task and worker-specific instructions. Source ↗
  • Returned output. The notebook returns the orchestrator analysis and individual worker responses as separate fields. Source ↗
  • Access. The public notebook uses Python and requires an Anthropic API key to run. Its helper sends requests to the Anthropic Messages API. Source ↗

Sources checked

Publisher update ·

Orchestrator-workers notebook updates its shared Claude model ↗

The example switched both the orchestrator and worker calls from Claude Sonnet 4.6 to Claude Sonnet 5.5.

Change timeline

0 stories

No verified releases in this timeline yet.