PythonAdvancedApplied AI EngineerForward Deployed EngineerApplied AI Architect
Multi-agent orchestrator
A lead agent that plans with structured output, runs isolated subagents in parallel with AsyncAnthropic, and synthesises, under enforced token, dollar and step budgets with JSONL tracing.
Locked
The code is part of the full course
The file map and notes are open to everyone. Get lifetime access to every template's source, the .zip download and all four tracks for a one-time $249.
Run it
shell
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # add ANTHROPIC_API_KEY
python -m app.main "Why did Q3 revenue fall, and what should we fix first?"Test it
shell
pytest -qOffline: no API key or network needed.
Taught in
- C10 Multi-Agent Architectures: Orchestrators, Handoffs and the Token Bill
- C10 Exercise: Single Agent or Orchestrator? A Cost Estimator
- C7 Sub-Agents in Practice: When Splitting Pays and When It Doesn't
- C7 Exercise: Fan Out a Contract Review, Then Prove It Paid Off
- E2 Sub-agents and Orchestrator-Workers
- E2 Exercise: An Orchestrator With Cheap, Isolated Workers
- C10 Reliability and Recovery: Idempotency, Checkpoints, Retries and Human Approval