Agent logs don't let us reconstruct "what the agent was thinking" at decision points
Observability for a production agent is limited to (a) LLM request/response pairs, (b) tool call inputs/outputs. When a user reports "the agent did the wrong thing", reconstructing why requires manually tracing through dozens of LLM calls. Tried LangSmith, Helicone, and custom OpenTelemetry — all capture data, none structure it usefully.