November 5, 2025
Catch issues before your users do
Detections are now on neatlogs. Rules that run against your traces automatically and flag the spans that match, no manual scanning.
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
Automatically flag runs that need attention
Surface important runs without manually inspecting every trace.
Create detections using regex patterns, numeric conditions, built-in PII detection, or semantic classifiers. Matching runs are automatically labeled in the traces list, and you can filter by detection type to quickly review related issues.
Release notesv0.6.0Flag important spans automaticallyNovember 2025
neatlogs can now run rules across your traces and mark the spans that match, so you can spot issues without opening every run one by one.
- FeatureCreate regex detections for exact patterns, condition detections for numeric thresholds like total_tokens > 8000 or latency_ms > 5000, and classifier detections for semantic checks that look at meaning instead of exact text.
- FeatureDetection badges now appear on the traces list, so you can scan runs at a glance and filter the entire list by detection type in one click.