{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "mikeparcewski-wicked-studio--approve-agent-work-with-evidence",
 "repo": "mikeparcewski/wicked-studio",
 "repo_url": "https://github.com/mikeparcewski/wicked-studio",
 "repo_slug": "mikeparcewski-wicked-studio",
 "title": "Approve agent changes using the assurance receipt",
 "page_title": "How to approve agent changes using the assurance receipt with Wicked Studio",
 "summary": "Check who built, evaluated and judged a change before you accept the delivery.",
 "who": "A reviewer who must sign off on agent-written code and needs to know how it was verified.",
 "problem": "An agent's claim of done says little about whether another seat checked the work or what was skipped.",
 "outcome": "You accept, steer or reject each gate with the assurance receipt, transcripts, diffs and evidence bundle in hand.",
 "steps": [
  "Open the run's session from the Desk so the gates that need you are listed first.",
  "Open a gate row and read the assurance receipt: required checks, seats that ran, skipped checks and the tree and attempt.",
  "Check the QE acceptance status shown on the session header, gate and delivery.",
  "Open the transcript and the worktree diff viewer for the files that changed.",
  "Download the evidence bundle, then approve, steer or reject the gate."
 ],
 "agent_prompt": "In the wicked-studio repo, open the session for <run id> and review its assurance receipt and gate rows. Expected output: a short note stating the assurance label, whether the builder and evaluator were separate seats, and any skipped checks. Verify that the note names the QE acceptance state exactly as the UI shows it.",
 "agents": [
  "claude-code",
  "codex"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "A run on a single seat is labelled Reduced assurance, so check the label before you treat the result as independently accepted.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "typescript",
 "requirements": [
  "Node.js 22 or newer and npm 10 or newer",
  "A container runtime for jobs: Rancher Desktop, Docker, Podman, Colima or OrbStack",
  "At least one coding-agent CLI you already use, such as Claude Code or Codex",
  "A modern browser such as Chrome, Edge, Firefox or Safari on macOS"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/mikeparcewski-wicked-studio/approve-agent-work-with-evidence/",
 "md": "https://dedupedai.com/use-cases/mikeparcewski-wicked-studio/approve-agent-work-with-evidence/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/mikeparcewski-wicked-studio--approve-agent-work-with-evidence.json",
 "api_version": "v1"
}