Observabilité LLM
Tracking what your AI app actually does in production: every model call, its cost, its latency, and above all the answer quality. An LLM app can fail without anything breaking: the server is green, the API is fast, and the chatbot still returns a wrong answer. Classic infra monitoring sees none of it. LLM observability captures the full trace (prompt, response, agent steps) so you can debug after the fact.
Strengths
- Replays the exact trace (prompt, response, agent steps) that produced a bug
- Measures cost and latency per call, not just in aggregate
- Serves as the base to wire evals and catch quality regressions
Limitations
- One more tool to instrument and maintain in the stack
- Traces contain user data: mind the retention scope
Best for
- An AI app or agent going to production in front of real users
- A team that wants to stop debugging hallucinations by gut feel