Encyclopedia Evalica / Evaluation / Confidence interval
Confidence interval
/'kah.nfuh.duhns 'ih.nter.vuhl/A statistical range around an estimate (e.g., mean score) that communicates uncertainty due to sample size/variance. Confidence intervals help prevent overreacting to noise. (noun)
“The confidence interval overlapped, so the 'improvement' wasn't statistically meaningful.”
Related Evaluation terms
- Absolute scoring •
- Agent •
- AI eval •
- Alignment •
- Annotation schema •
- Baseline •
- Baseline experiment •
- Benchmark •
- Calibration •
- CI/CD integration •
- Coherence •
- Eval harness •
- Eval leakage •
- Experiment •
- Factuality •
- Failure mode •
- Faithfulness •
- Feedback signal •
- Groundedness •
- Hallucination •
- Inter-annotator agreement (IAA) •
- LLM-as-a-judge •
- Loop •
- Model comparison •
- Multimodal •
- Non-determinism •
- Offline evaluation •
- Pairwise evaluation •
- Pass@k •
- Playground •
- Quality gate •
- RAG (retrieval-augmented generation) •
- RAG evaluation •
- Reference-based scoring •
- Reference-free scoring •
- Regression testing •
- Release criteria •
- Remote evaluation •
- Rubric •
- Safety •
- Score distribution •
- Scorer •
- Semantic failure •
- Signal-to-noise ratio •
- Task (eval task) •
- Toxicity score
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