GlossaryOriginSpecs

Glossary

Declared Policy

A Declared Policy is an agent's committed rules of conduct for a run, its allowed tools and arguments, egress destinations, data scopes, credentials, delegation targets and memory stores, hashed, anchored and published to the Registry before any bait is released.

ProofJack Rating: Human 25% · AI 75% (self-estimated; PP-SPEC-078 AI_DISCLOSURE: Declared Policy proposed by Claude)

Also known as: IP-J1, Policy Provider, agent policy, policy drift

Mynted 2026-10-23 · Updated 2026-10-23

First used: PP-SPEC-078, No Bros Jail Mode Protocol: The Jailed Canary Protocol, October 2026, by Craig Thomas Ellrod

What it means

You cannot judge an agent’s conduct against rules written after the fact. The Declared Policy is the line, drawn and sealed in public before the test, that the Warden enforces and the Adjudicator judges against.

The rules

Related terms

Sources

Updated 2026-10-23