skip to content

Analysis / Business automation and AI evaluation

Score AI extraction against reference fields

Score AI extraction in Proforma against reviewed reference fields. Separate missing, incorrect and unsupported values, with document-type failure examples.

A starting point for

AI automation lead

Bring this question into Chat

Your starting prompt.

Evaluate [AI extraction workflow] against [reviewed reference fields] on [permitted documents]. Define field-specific matching and normalization rules before scoring, separating missing, incorrect and unsupported values. Show results by document type and field with actual failure examples. Preserve source references and the exact schema, prompt and model used. Do not reward plausible invented values or treat a format-valid object as semantically correct extraction.

Copy this starting point, then replace the placeholders with your own inputs.

Method and review

Keep the assumptions visible.

Define inputs, outputs, permissions and failure conditions before implementing an Action. Evaluate AI against representative labeled examples and retain human approval for consequential steps.

For this task, check

Reviewers should check the reference set and normalization rules before interpreting extraction quality.

This starting prompt has no published worked example yet. Begin with a small sample and check the calculations before relying on the result.

Before you begin

  • Permitted documents with reviewed reference fields
  • Configured AI runtime
  • Agreed matching and normalization rules

Work with permitted files or queryable data. Verify the result against the original records.

Take the next step

Make it your investigation.

Copy the prompt above, create or open your Workspace, and paste it into Chat. Add the inputs you have permission to use and adapt the assumptions with your agent.

Start exploring

Your prompt is carried by copy and paste. Signing up does not submit it or start this work automatically.

Or start with your own agent

The setup prompt includes this public task. Your agent will help you connect when needed and use the access you approve.

Choose Claude, Codex, or Cursor—or copy the prompt to use anywhere.