Encyclopedia Evalica / Observability / Logs
Logs
/lawgz/Capturing structured execution data from both development and production environments. In AI observability, logs are trace-based rather than line-based. (noun)
“We enabled logging in prod so we could reproduce the bug from real user traffic.”
Customer example
Retool logs production agent behavior and then queries those logs to prioritize fixes by "blast radius" and to understand system health as Assist scaled beyond what manual QA could handle. Read more
Related Observability terms
- AI observability •
- Alert / threshold •
- Dashboard •
- Data flywheel •
- Deep search •
- Drift •
- Error rate •
- Feedback loop •
- Model drift •
- Online evaluation (production scoring) •
- P50 / P95 / P99 (Percentiles) •
- Sampling rate •
- Service Level Indicator (SLI) •
- Service Level Objective (SLO) •
- Time-to-first-token (TTFT) •
- Token usage / cost tracking •
- Topics
From the docs
Get started with Evals
Braintrust is the AI observability and eval platform for production AI. By connecting evals and observability in one workflow, teams at Notion, Stripe, Zapier, Vercel, and Ramp ship quality AI products at scale.
Start building