Curriculum
Module 12
Observability and debugging runs
Reading a trace of something that will not repeat: what to log, tracing a run end to end, reproducing a bad run, and monitoring one in production.
4 lessons · 11 videos · 3h 2m- 12.01
Tracing a run
Capture every step of an agent run so a failure can be read afterwards.
- 12.02
What to log when the output is not stable
Log the inputs, the tool calls and the decisions, not just the final answer.
- 12.03
Reproducing a bad run
Replay a failure closely enough to fix it, given temperature and tool state.
- 12.04
Knowing it broke before a user says so
Alert on the agent-specific signals: loop length, tool error rate, cost per run.