{
  "schema_version": "1.1",
  "id": "p5",
  "slug": "eval-harness-post",
  "url": "https://feed7.dev/p/eval-harness-post",
  "title": "A minimal eval harness you can run in CI",
  "why_included": "Shows how to gate agent changes behind a tiny, fast eval set in CI.",
  "summary": "A 20-case eval wired into CI that fails the build on regression. Full code in the post; runs in under 30 seconds.",
  "practical_implication": "Makes agent reliability a CI concern, not a vibe. Start with your 5 most common failure cases.",
  "agent_context": "Wire a 20-case eval into CI; fail the build on regression. Keep it fast (<30s) so agents get feedback each PR.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/blog/minimal-eval-harness-ci",
    "published_at": "2026-06-26T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "benchmark",
  "domains": [
    "coding"
  ],
  "topics": [
    "agent-evals"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [],
  "connected_context": null,
  "lifecycle": "New",
  "published_at": "2026-06-26T00:00:00.000Z",
  "modified_at": "2026-06-26T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/eval-harness-post",
    "json": "https://feed7.dev/p/eval-harness-post.json",
    "markdown": "https://feed7.dev/p/eval-harness-post.md"
  }
}