RRubric
Witness Layer · Live Demonstration
Agentic AI · Witnessed

An AI made a hiring decision.
Prove what it actually did.

Three AI agents evaluate candidates for a real role. Each decision is witnessed by Rubric — signed with post-quantum cryptography and chained to the one before it. When the decision is challenged months later, the record cannot be quietly rewritten.

Rubric does not judge whether the decision was fair. It proves what the decision was — so it can't be changed after the fact.
IThe agents evaluate

Real language-model agents, running in sequence: one parses each résumé, one scores it against the role's stated criteria, one issues a disposition. Every step is attested to Rubric as it happens. representative candidates · real AI reasoning

IIThe record, six months later

One candidate — Candidate B — was rejected, and has filed a discrimination claim. Counsel asks: what did the AI actually decide, and on what basis? Rubric reconstructs the exact decision chain. Verify it against the ledger — the cryptography runs right here, in your browser.

IIISomeone alters the record

Imagine the rejection rationale is quietly edited after the claim is filed — changed to look more defensible. The data on disk now says something different. Re-run the very same verification against the altered record.

Signed with ML-DSA-65 · Canonicalized per RFC 8785 · Anchored to a public ledger
Every attestation in this demonstration is real. Verify them yourself — the keys and signatures are embedded in this page.