CloudFixies mascot logo CloudFixies.
← All articles
AI Agents

Agent observability — what to log

When the agent does the wrong thing, you have hours (not weeks) to understand why. Log accordingly.

Published by CloudFixies · 30 December 2025

The minimum trace

Every turn: input, tool calls (with arguments), tool responses, model output, latency, tokens, user identity. Everything hashed if it contains PII. Retained for 90 days, then aggregated.

What to skip

Full document contents. Verbose model reasoning that isn’t action-relevant. Anything that recreates the PII you just went to the trouble of not storing.

◆ Takeaway

Log tool calls and outcomes, not stream-of-consciousness reasoning.

← Prompt injection in 2026 Model-agnostic agents — a realistic approach →