Encyclopedia Evalica / Observability / P50 / P95 / P99 (Percentiles)
P50 / P95 / P99 (Percentiles)
/'pee.fifty slash 'pee.ninetyfive slash 'pee.ninetynine per'seh.nteyelz/Latency percentiles used to describe typical vs. tail performance. Tail latency (P95/P99) often matters more for user experience than the average. (noun)
“P95 jumped after we enabled a heavier retrieval step.”
Related Observability terms
- Active observability •
- AI observability •
- Alert / threshold •
- Dashboard •
- Data flywheel •
- Deep search •
- Drift •
- Error rate •
- Feedback loop •
- Logs •
- Model drift •
- Online evaluation (production scoring) •
- 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 observability platform for agents in production. By actively applying intelligence to agent traces and automatically surfacing critical patterns, Braintrust helps teams at Notion, Stripe, Box, OpenAI, and Cloudflare ship quality agents at scale.
Start building