Encyclopedia Evalica / Observability / Drift
Drift
/drihft/A gradual shift in the distribution of inputs, outputs, or scores over time. Drift can signal changes in user behavior, model degradation, or upstream product changes. (noun)
“The dashboard flagged drift as user questions shifted from setup to troubleshooting.”
Customer example
Retool monitors for drift week-over-week using production metrics and traces, with dashboards and Loop to spot shifts in failure patterns as Assist scales. Read more
Related Observability terms
- Active observability •
- AI observability •
- Alert / threshold •
- Dashboard •
- Data flywheel •
- Deep search •
- Error rate •
- Feedback loop •
- Logs •
- 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 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