Observability and logs

Inhalt

Observability means capturing what the system did, what input it received, what outputs it produced, which tools were called, and where failures occurred. This is essential for debugging, accountability, and reproducibility. Minimum fields per row: timestamp, input hash (not raw input, if sensitive), model + tokens, tool calls, output snippet, rubric score. Log before and after every LLM call — "what we sent" vs "what it returned" is the most valuable diff you'll ever have.

Beispiel: A log shows: abstract X was processed, classified as "methods", routed to branch 2, reviewed with score 3/4, and delivered to PI inbox at 14:07.

Hast du das verstanden?

• [ ] Every log row has timestamp, run_id, model, token counts, and output snippet
• [ ] You reconstructed one past run purely from the log
• [ ] Sensitive inputs are hashed or redacted in the log
• [ ] You can write one SQL query to count failures this week
• [ ] You can explain in one sentence what you learned that you would tell a labmate tomorrow

Direkt ausprobieren

Diese Links öffnen die laufenden Demos auf n8n.32dots.de + dify.32dots.de.