book an evals working session with us
All updates

March 5, 2026

Version your prompts like code

Prompt management is now on neatlogs. Every edit creates a new version. Promote to production with a label change, no redeploy needed.

Updates
  1. Write detections in codeSeptember 7, 2026
  2. Review traces with AI evaluatorsJuly 27, 2026
  3. Replay an agent run step by stepJuly 1, 2026
  4. See cost, latency, and errors across every runJune 16, 2026
  5. Triage in Your EditorMay 29, 2026
  6. Import Your Traces from LangSmith and BraintrustMay 28, 2026
  7. Ask your trace data anythingMay 1, 2026
  8. Keep sensitive data out of your tracesApril 12, 2026
  9. Version your prompts like codeMarch 5, 2026
  10. Instrument multi-turn conversationsJanuary 20, 2026
  11. Collaborate on traces with your teamDecember 10, 2025
  12. See exactly what your AI agent didNovember 18, 2025
  13. Catch issues before your users doNovember 5, 2025
  14. Zero-config observability for every frameworkOctober 22, 2025
Version your prompts like code

Manage prompts without redeploying

Update prompts independently of your application code.

Store prompts in Neatlogs and fetch them at runtime instead of hardcoding them. Test changes in the Playground before promoting them to production, keep a complete version history, and roll back instantly if needed.

If you're already using Langfuse, you can import your existing prompts from Experiments → Prompts → Import.

prompt = neatlogs.get_prompt("system-prompt", label="production")
compiled = prompt.compile(user_name="Alex")
Read the Experiments docs
Release notesv0.9.0Experiments: Prompts & PlaygroundFebruary 2026

Version-controlled prompt storage with production and staging labels. Test prompt changes in the Playground sandbox before shipping to production.

  • FeaturePrompt versioning: every edit creates a new version with full history and one-click rollback
  • FeatureLabels (production, staging) for fetching the right version at runtime via neatlogs.get_prompt()
  • FeaturePlayground sandbox: test prompt changes against live model calls before deployment
  • Featureneatlogs.get_prompt(), update_prompt(), save_as_version(), list_prompts() SDK methods
  • FeatureImport prompts from Langfuse via Experiments > Prompts > Import