Human review

/'hyoo.muhn ree'vyoo/A workflow in which team members manually examine and score traces or dataset records through a dedicated UI. Human review is often reserved for high-risk or high-impact cases. (noun)

“We scheduled human review for the most sensitive edge cases before the launch.”

Customer example

Navan's ops team reviews only the subset of calls that the eval system flagged for follow-up. Read more

Related Annotation terms

Annotation

•

Label

From the docs

Annotate and curate data

•

Add human feedback

•

Add labels and corrections

•

Configure human review visibility in dataset views

•

Fetching human review comments via API and BTQL

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.