Testing

This earlier topic now connects to the agent systems writing. These are useful places to continue:

• Before You Build Another Agent — Start with one capable generalist. Add delegation only when the task earns it.
• Trustworthy Autonomy — Design evidence, ownership, permissions, and recovery as runtime guarantees.
• How to Write and Score an Agent Eval — A worked incident, scoring explorer, and runnable Python companion.
• Checkpoint Replay for Long-Horizon Agent Evaluation — Freeze what the agent could know at each decision.
• Classifiers: When Labels Become Decisions — Build a label policy and measure the errors your decision can tolerate.