Ship and explain the research bot capstone

From a fresh clone/directory, run the commands that prove brief on fixture corpus: ≥ 0.95 claims cited; fabricated ID rate 0. A second person plays analyst compiling a brief on bike-share policy from a fixed corpus and follows your script without coaching. The demo includes limitations: what citation-first research assistant that maps every claim to evidence IDs still will not do.

Bundle: contract snippet, passing tests, metric snapshot for claim_citation_coverage and fabricated_id_rate, security negative probe, rollback note, owner name. Reference CAP-RESEARCH-FAKE-ID-3 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.

For Capstone: research bot with citations, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint POST /v1/research/brief remains the production surface you operate for citation-first research assistant that maps every claim to evidence IDs — not a slide. Keep CAP-RESEARCH-FAKE-ID-3 in the handoff template so the next owner inherits the drill.

After the peer demo, schedule the next threshold review date. File a short changelog that mentions CAP-RESEARCH-FAKE-ID-3 and the control that addresses it. Archive the evidence pack where your team already stores launch records. Resist rewriting everything “for real production” in one weekend — operate this slice until the metrics bore you, then widen. Final self-check: if telemetry vanished, would you still know to hold? If yes, you learned the operating posture this lane teaches.

Trim the demo script until every command is necessary. Record a peer signature line: name, date UTC, pass/fail. File known limitations as bullets, not apologies. Link the evidence pack from the README. Schedule the next game day on a calendar, even if it is solo. Archive the branch tag or release digest you actually shipped. In this chapter the product is citation-first research assistant that maps every claim to evidence IDs, the human stakeholder is analyst compiling a brief on bike-share policy from a fixed corpus, and the incident id you design against is CAP-RESEARCH-FAKE-ID-3. Re-state the oracle in your notes — brief on fixture corpus: ≥ 0.95 claims cited; fabricated ID rate 0 — and keep the invariant visible: claim without evidence → abstain or drop claim; no orphan sentences. Track claim_citation_coverage and fabricated_id_rate as the scoreboard. Surface under change control: POST /v1/research/brief. If you only have forty minutes, finish the fixture for model invents kb://minutes-2099 citation before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.