{
  "schema_version": "1.1",
  "id": "p14",
  "slug": "linkedin-eval-rollout",
  "url": "https://feed7.dev/p/linkedin-eval-rollout",
  "title": "Rolling out agents behind evals — an operator’s playbook",
  "why_included": "Concrete staged-rollout playbook with numbers — but the claimed win rates are not yet source-linked.",
  "summary": "Operator describes gating an internal agent behind a 40-case eval, canarying to 10% of tasks, then expanding. Claims 30% fewer escalations.",
  "practical_implication": "The staging pattern is reusable today; treat the win-rate numbers as unverified until the promised write-up lands.",
  "agent_context": "Staged agent rollout: gate behind eval set, canary 10% of tasks, expand on pass. Pattern is sound; the 30% improvement claim is unverified.",
  "source": {
    "name": "LinkedIn",
    "url": "https://www.linkedin.com/posts/operator-evals-rollout",
    "published_at": "2026-07-01T00:00:00.000Z"
  },
  "source_class": "social_media",
  "content_type": "Social Thread",
  "layer": "benchmark",
  "domains": [
    "coding"
  ],
  "topics": [
    "agent-evals",
    "agent-reliability"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "Win-rate numbers not source-linked; write-up promised but not published."
  ],
  "connected_context": null,
  "lifecycle": "New",
  "published_at": "2026-07-01T00:00:00.000Z",
  "modified_at": "2026-07-01T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/linkedin-eval-rollout",
    "json": "https://feed7.dev/p/linkedin-eval-rollout.json",
    "markdown": "https://feed7.dev/p/linkedin-eval-rollout.md"
  }
}