> ## Documentation Index
> Fetch the complete documentation index at: https://docs.captar.aurat.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Manual Evals

> Launch reviewer runs from datasets and score rows with pass or fail plus rubric criteria.

# Manual Evals

Manual evals are the current evaluation workflow in Captar v1. They let teams
review dataset rows with pass or fail verdicts, notes, and weighted rubric scores.

## Current workflow

<Steps>
  <Step>Create a manual eval from an existing dataset.</Step>
  <Step>Add reviewer instructions and weighted criteria.</Step>
  <Step>Start a run.</Step>
  <Step>Review rows, score criteria, and record verdicts.</Step>
</Steps>

<Callout type="warning" title="Manual review only in v1">
  Automated evaluators and live evaluation pipelines are intentionally out of
  scope right now. The shipped workflow is manual review backed by datasets.
</Callout>