Never regress
State advances only when every declared check passes and nothing that passed before fails.
Verification infrastructure for AI agents
GenXis Gavel is an independent verification authority for AI-generated work. It runs the checks you declared, refuses to certify anything it cannot decide, and signs a receipt for every verdict, so "done" from an agent means something.
State advances only when every declared check passes and nothing that passed before fails.
The model that proposes can never grade itself. Independent primary and shadow verifiers agree, or the answer is DENY.
Ed25519-signed, hash-chained, and replayable from the artifact root by anyone, offline.
For developers
Point Gavel at an artifact (a staged diff, a file, a test run, a JSON payload) plus a pre-committed oracle. It returns PROMOTE or DENY, the exact evidence, and a receipt you can verify without us. Call it from the CLI, an MCP tool, an OpenAI-compatible endpoint, or a pre-commit and CI hook. The same authority runs our public open-model benchmark at mostannoying.ai: 100 frozen tasks in five packs, every certified catch linked to its evidence.
Request
Gavel verdict
Pre-edit, final-diff, and CI boundaries inside the agent workflow you already use, in observe, ask, or deny mode.
Commands, test suites, JSON schema, exact output. Every oracle is hashed and frozen before the run. No oracle, no verdict: it refuses rather than guesses.
Every verdict re-runs from its recorded roots. Denials, duplicates, timeouts, and regressions are never billed as catches.
Our principles
Every rule below is enforced in code and shows up in the receipt, not on a slide.
Proposers propose. Only Gavel promotes. A model cannot score, certify, or bill its own output.
Missing oracle, drifted source, mismatched hash, truncated response: Gavel stops and says exactly why. Unverified is never relabelled as pass.
Raw provider bytes are stored before they are parsed. Every dispatch, retry, and cent lands in a hash-chained ledger you can audit.
Nothing runs without a signed owner authorization bound to one exact proposal hash. One shot, no silent retries, explicit spend and wall-clock caps.
These aren't slogans. They're gates the system fails closed on.
Company
GenXis builds the control plane that lets AI systems get better without getting away from you: verified memory that keeps only what passed, counterexamples that compound into faster search, typed source-bound edits with machine-generated diffs, and improvement that has to beat its own control arms before it is promoted.
Independent primary and shadow checks against a frozen contract.
Only a strict PROMOTE advances state. Everything else is recorded and denied.
Verified lessons feed the next run. Control arms prove the memory is doing the work.
Latest controlled run: 12 of 12 unseen tasks with verified memory, 3 to 4 of 12 without it. Zero retries, $0.04 spent, every result under a Gavel receipt.
Build with us