{
  "schema_version": "1.1",
  "id": "p10",
  "slug": "evals-workshop-aie",
  "url": "https://feed7.dev/p/evals-workshop-aie",
  "title": "Building eval sets that survive model swaps — AI Engineer workshop",
  "why_included": "Eval sets usually die when you change models. This workshop shows how to write ones that transfer.",
  "summary": "Behavior-anchored evals: assert on user-visible outcomes, not model phrasing. Includes a template repo and a live migration from GPT to Claude.",
  "practical_implication": "Rewrite phrasing-based assertions as outcome assertions now — before your next model swap forces it.",
  "agent_context": "Write evals against user-visible outcomes, not model phrasing. Outcome-anchored evals survive model swaps. Template: given/when/then on behavior, never on wording.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=ai-eng-evals-2026",
    "published_at": "2026-06-21T00:00:00.000Z"
  },
  "source_class": "video",
  "content_type": "Workshop",
  "layer": "benchmark",
  "domains": [
    "coding"
  ],
  "topics": [
    "agent-evals",
    "model-selection"
  ],
  "verification": {
    "status": "transcript_verified",
    "label": "Transcript Verified",
    "method": "transcript_review",
    "verified_at": null
  },
  "uncertainty": [],
  "connected_context": null,
  "lifecycle": "Evergreen",
  "published_at": "2026-06-21T00:00:00.000Z",
  "modified_at": "2026-06-21T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/evals-workshop-aie",
    "json": "https://feed7.dev/p/evals-workshop-aie.json",
    "markdown": "https://feed7.dev/p/evals-workshop-aie.md"
  }
}