The outcome

Maintain useful production observability without creating an uncontrolled secondary store of prompts, documents, or credentials.

Step by step

A workflow you can repeat.

  1. 01

    Map every field that tracing can capture, classify sensitivity, choose cloud or self-hosted boundaries, and define sampling, retention, deletion, access, incident, and legal policies.

  2. 02

    Use separate scoped keys and projects per environment, redact before export, disable tracing conditionally for sensitive tenants, and attach only non-secret version and routing metadata.

  3. 03

    Sample normal traffic and fully capture approved error classes, validate parent-child spans and tool outcomes, and alert on safety, schema, latency, cost, and failure signals.

  4. 04

    Restrict workspace and dataset access, review online evaluator filters and spend, test trace and dataset deletion, and verify that tracing can be disabled during an incident.

  5. 05

    Audit access, sampling, retention, redaction, evaluator versions, and unresolved traces regularly, exporting only necessary evidence and documenting every policy change.

Working standard

What good use looks like.

  • Redact before traces leave the app.
  • Separate environments and tenants.
  • Test deletion and tracing shutdown.

Official references

Check the current product documentation.