Agentic Representation: Evidence, Selection and Warrant in AI-Assisted Reports

An AI-assisted report can cite its sources accurately and still leave a reader with a conclusion those sources do not support. The difficulty may lie in which evidence it selects, how it connects observations, or whether it preserves the difference between an initial finding and its later correction. This paper proposes agentic representation as a research programme concerned with accounts produced through workflows of retrieval, selection, synthesis and revision. It distinguishes support for individual claims, adequacy of an account for a stated question, and the conclusions readers draw from it. Historical source criticism and the philosophy of representation help formulate these distinctions; existing work on argumentation, evidence synthesis, summarisation, framing and misleading omission supplies substantial precedents. The proposed application is therefore narrow: reports assembled from institutional records whose evidential status changes over time. A worked hypothetical case motivates a method that records the relationships between conclusions, evidence, qualifications and corrections. A prospective study would compare this method with competent general review and a simpler checklist under comparable resource constraints. It would measure reader understanding, successful correction, false challenges to adequate accounts and human effort. This first comparison supplies the complete dossier and holds the reviewing model fixed. It tests the account-record procedure, not retrieval, handover or a benefit from multiple agents. The paper offers a conceptual framework and an evaluation proposal. Whether the method improves practice remains open. Conceptual preprint; not peer reviewed. The proposed study has not been run. AI-assisted manuscript criticism and its limits are described in the accompanying review summary.