Agent Search QA Bench - Source Code Starter

Evaluation dashboard for AI search and browser-agent outputs. Tracks citations, unsupported claims, extraction accuracy, source quality, and reviewer actions.

What buyers get:

- Static dashboard source code

- Sample evaluation CSV

- Citation and unsupported-claim scoring

- Failed-run triage views

- Markdown QA report export

- README, pricing notes, and transfer notes

Best fit: AI agencies, research teams, SEO operators, browser-agent builders, and technical freelancers who need reusable QA reports for AI-generated research.

Current status: working source-code starter with demo data. Pre-revenue; no users, traffic, or revenue are claimed.