# Governed Agent Recipes — four runnable Python agents with governance wired in | Series A PR reviewer with subagent delegation, a SQL agent with PII scrubbing, a 4-hop research agent, and a human-in-the-loop email triage agent — full working code, ~200 lines each, every tool call identified, policy-checked, and audited.
Recipe series

Agent Recipes with Rules

Four complete, runnable Python agents — each one shipping with identity, per-call policy, and an audit chain from line one, not bolted on later. Copy the file, run it, watch every tool call land in your audit log. Around 200 lines each.

New to the concepts? Start with runtime authorization and delegation chains — every recipe uses both.

Posts in this series

Each recipe is a different control pattern: delegation, tool-output redaction, deep chains, and human-in-the-loop approval.

  1. .