RAVEN. / anti-slopRAVEN. / anti-slopAgents generate convincing text, code, summaries, and UI. None of it is launch evidence unless Raven checked the supported evidence and signed a receipt. Raven's job: a crisp boundary between "the agent said" and "the verifier checked". Machine-readable: /anti-slop-policy.json.
An LLM may explain a receipt, summarize findings, and help gather context to ASK Raven about. It may not alter a receipt, upgrade a verdict, remove coverage gaps, convert pass into "safe", treat missing evidence as a pass, or override staleness. Derived interpretations may only hold or DOWNGRADE confidence — never upgrade it.
Any summary of a receipt must preserve: verdict, finding codes, coverage gaps, keyId, engine version, observed slot, signature status, staleness status, and the policy action. Forbidden: omitting gaps, vague paraphrases of finding codes, "safe/approved/good to buy", hiding failures, converting unknowable into pass. With gaps remaining the summary says: not enough evidence for a full pass. The summary is never authority; the receipt is.
AI-generated integration code is untrusted until tests pass: valid-signature verification, tampered/missing-signature rejection, unknown-keyId rejection, fail-closed verifier errors, stale handling, gap preservation, correct verdict mapping, no "safe", no secret logging, no browser keys, no wallet signer permission. No publish without human approval. Raven practices this on itself — our Agent Kit plugin shipped only after fixture + live tests.