Product
Document Extraction QA
Document Extraction QA
Start with Source documents + extracted records. Uploaded files describe a snapshot. Supply new files for new private facts; prior cases remain available for comparison. Tests and measurements require actual execution evidence; unavailable capabilities remain visible as coverage gaps.
- 1/wkEvidence reports
FactoriesStart with your sources
IdleIllustrative runWalking critical flows onapp.example.com
src/server/cart/summary.ts
- Flows walked
- 0
- Draft pull requests
- 0
Draft pull requestfix/checkout-summary-no-discount into your default branch
Fix checkout summary for carts with no discount
Related solutions
See how teams in this category put agents to work.
Integrations
0 integrationsGet started with Document Extraction QA
Pick an example, connect your tools, and review the first run.
Set up the Document Extraction QA agent template for this project. Follow /SKILL.md for the exact CLI commands.
Goal: Compare fields with source evidence, investigate plausible-looking errors, and maintain corrected records, layout-specific examples, and extraction improvements.
1. Install the CLI if it is not on PATH, check that I am signed in, and select my team and project.
2. List the first-party workflow templates. If `document-extraction-qa` is listed, instantiate it with `--path.slug document-extraction-qa` and start the run; otherwise create a project from this template at /new?template=document-extraction-qa&preset=trial.
3. Share the run id, follow the run until it finishes, and summarize its outputs and changes.
Ask me before spending FTAI or changing anything outside this repository.
Launch from Claude Code, Codex, Cursor, and other agents.