September 7, 2026
Write detections in code
Regex and thresholds are great for common patterns. But sometimes the thing you care about is more specific.
Updates
- Write detections in codeSeptember 7, 2026
- Review traces with AI evaluatorsJuly 27, 2026
- Replay an agent run step by stepJuly 1, 2026
- See cost, latency, and errors across every runJune 16, 2026
- Triage in Your EditorMay 29, 2026
- Import Your Traces from LangSmith and BraintrustMay 28, 2026
- Ask your trace data anythingMay 1, 2026
- Keep sensitive data out of your tracesApril 12, 2026
- Version your prompts like codeMarch 5, 2026
- Instrument multi-turn conversationsJanuary 20, 2026
- Collaborate on traces with your teamDecember 10, 2025
- See exactly what your AI agent didNovember 18, 2025
- Catch issues before your users doNovember 5, 2025
- Zero-config observability for every frameworkOctober 22, 2025

How it works
You can now write custom function detections in neatlogs. Pick a target, write a function, and return a boolean. Your code runs against a snapshot of every span or trace in scope, and anything that returns true gets flagged.
Use it for checks that need your own logic, like marking traces where cost, latency, metadata, and span content combine in a way simple rules can’t express. You can also train a classifier on your own labeled spans and run it across your traces as a detection, giving you another way to catch patterns that are easier to recognize than hard-code.
Release notesv1.17.0Custom function detectionsSeptember 2026
Write detection logic in code and run it across every span or trace in scope.
- EnhancementCost analytics by metadata: Group trace cost by any metadata key, so you can see spend by customer, feature, model, or any other tag you send.
- EnhancementBroader PII redaction: Server-side redaction now covers every supported span kind.
- FixedMore reliable trends and evals: Detection trends and evals now handle large repeated query arrays more gracefully.