Adversarial QC

Structured quality control for AI deliverables. Two agents independently verify a deliverable against a checklist, then results are compared. Agreements = high confidence. Disagreements = flagged for human review.

Quick Start

1. Read the deliverable to be reviewed
2. Read references/checklist.md for the verification checklist
3. Read references/config.md for model configuration
4. Run the QC process (see Workflow below)
5. Generate the QC certificate

Configuration

The user controls these settings. Ask if not specified: