Research papers, technical reports, and the evidence behind our systems.
Each publication has a stable page for its contribution, evidence, limitations, artifacts, and citation. New work is added here as it becomes publicly available.
A claim-carrying mediation layer that converts decision-relevant rationale content into typed action claims and verifies them against current server-held facts before governed execution.
→A server-side authorization layer that binds tool visibility and proposed effects to the user’s current expressed intent—narrowing, never expanding, existing authority.
→A governance-first specification for exposing application tools to AI agents through server-side authorization, reviewable writes, predictable failure semantics, and audit.
→Additional publications will appear here as they become publicly available.
