DSME Global Links
DSME Global Links
Engineering

LLM observability: what to log and what to watch

You cannot debug what you did not record. The traces, metrics and samples worth capturing before your AI feature meets real users.

Marcus Reid·Principal Engineer·July 1, 2026·6 min read

Conventional monitoring tells you the request returned 200 in 800ms. For an AI feature that is close to useless — the interesting failures all return 200 with a confident, wrong answer.

Log the whole chain, not the call

One user question can involve a rewrite, a retrieval, a rerank, two model calls and a tool invocation. Logging only the final call leaves you unable to answer the one question that matters: which step went wrong? Trace the chain with a shared id.

  • The original input and the rewritten query
  • Retrieved chunks with scores, and which ones the answer actually used
  • Full prompt as sent, including the resolved system prompt and prompt version
  • Raw model output before parsing
  • Tokens, latency and cost per step

One question, many steps — trace all of them

Logging only the final model call leaves you unable to say which step failed.

Post-processing

Validation, repair, fallback taken

Model call

Raw output before parsing, tokens, latency, cost

Prompt assembly

Full prompt as sent, plus prompt version

Retrieval

Chunks returned, with scores

Query rewrite

What you actually searched for

User input

Original text, before any rewriting

Watch the metrics that predict complaints

Refusal rate, retrieval-miss rate, fallback rate and the share of low-confidence answers all move before your satisfaction scores do. Alert on those and you find problems while they are still small.

Metrics that move before complaints do

  • Refusal rate climbingRetrieval is missing
  • Fallback rate climbingPrimary path is failing quietly
  • Low-confidence share climbingContent or questions have shifted
  • Satisfaction droppingYou found out last

Sample and read the transcripts

Automated evals catch what you thought to test. Reading fifty real conversations a week catches everything else — and it is the single habit that most reliably improves an AI product. Rotate who does it.

Mind what you are storing

These logs contain user input, which frequently contains personal data. Decide retention deliberately, redact at capture rather than at read time, and make sure your logging story is one you would be comfortable explaining to the customer whose data is in it.

M
Written by
Marcus Reid
Principal Engineer, DSME Global Links