All guides

Production AI Radar

How to trace and debug LLM apps with Arize Phoenix

Open instrumentation for spans, retrieval, and eval overlays — find why a RAG answer failed in minutes, not days.

TrialObservability11 min
RAG pipeline · eval gates

Hover a node · click to focus · ←/→ steps

Ingest → embed → index → retrieve → generate. Offline + online eval gates block regressions before promote.

When you need this

  • Langfuse alone is not enough for notebook-to-prod debugging
  • Need local/OSS tracing before enterprise APM spend
  • Retrieval quality opaque in production traces
  • Want span-level eval overlays

Prerequisites

  • App or gateway you can instrument
  • Phoenix deployment (local or hosted)
  • PII redaction policy for stored spans

Tools

  • Strong OSS alternative or complement to Langfuse; evaluate self-host ops.

  • Instrument gateway and app tier first; expand to training jobs later.

  • Wire into CI with a fixed golden set - do not rely on LLM-judge alone without human calibration.

Steps

  1. 1

    Instrument the critical path

    Trace LLM calls, retrieval, and tool use. Propagate IDs through the gateway. Redact PII before export.

  2. 2

    Stand up Phoenix

    Run Phoenix for the team; import traces. Confirm engineers can open a failing user session end-to-end.

  3. 3

    Overlay evals

    Attach Ragas/faithfulness scores to spans. Filter traces by low scores for triage queues.

  4. 4

    Feed the release loop

    Sample failing online traces into the golden set monthly so offline evals track real failures.

Adoption pitfalls

  • Storing raw PII in traces
  • Instrumenting everything with no sampling → cost and noise
  • Traces without product/team tags

Adoption checklist

  • Critical LLM path fully traced
  • PII policy applied to spans
  • Low-score triage queue owned
  • Monthly golden-set refresh from prod failures

SEER REAL assessment / sprint

Assessment checks debug time for a recent LLM incident. Sprint instruments one path into Phoenix with eval overlays and a triage ritual.

Related radar blips