RedHub AI
How the gate works
How the AI Deliverable Claim & Citation Defensibility gate works
This tool grades a finished AI-assisted deliverable claim by claim - citation present, reachable, and actually supporting the claim. It scores 5 weighted controls into a 0–100 number — then a gate that can only make the verdict worse.
The 5 weighted controls
Any claim marked material whose citation is unreachable (citation reachable = 0) or that shows a fabrication tell (fabrication-free = 0) forces DO NOT SHIP for the whole deliverable, independent of the blended score - one indefensible material claim voids the rest, no matter how clean the others read.
Why: Nine claims, six material. The blended defensibility score is 89/100 - six claims are perfectly SUPPORTED and only one non-material claim (C09) needs a second look - which would normally read DEFENSIBLE. But two material claims fail outright: C03's citation is unreachable and C06 shows a fabrication tell. Either one alone holds the deliverable - the gate forces DO NOT SHIP regardless of the 89.
A high score didn’t save it. The score is context; the gate is the answer — and it names the one thing to fix first. Not a guarantee of accuracy or a substitute for subject-matter review. A review aid for your own deliverables - it grades claims, never people. Not legal advice.