{
  "schema_version": "1.0",
  "id": "s8:https://www.youtube.com/watch?v=xIt_mTQp6mY",
  "slug": "loop-engineering-from-first-principles-kyle-mistele-humanlayer-1nuq7gf",
  "url": "https://feed7.dev/p/loop-engineering-from-first-principles-kyle-mistele-humanlayer-1nuq7gf",
  "title": "Loop Engineering from First Principles — Kyle Mistele, HumanLayer",
  "why_included": "Replace unbounded coding-agent loops with measured, incremental changes: sense code state, choose one bounded task, open a reviewable PR, and pause until a human responds.",
  "summary": "HumanLayer frames coding automation as **sense → control → actuate**: detect a measurable code condition, select a bounded change, and give an agent a skill plus handwritten reference patterns. Their workflow schedules **one incremental PR per day**.",
  "practical_implication": "Build loops around deterministic scanners, small changes, CI, and human review. Keep **at most one open PR per loop**, then feed reviewer corrections back into the skill before the next run. Increase throughput only after the loop is reliable.",
  "agent_context": "HumanLayer frames coding automation as **sense → control → actuate**: detect a measurable code condition, select a bounded change, and give an agent a skill plus handwritten reference patterns. Their workflow schedules **one incremental PR per day**.\n\nBuild loops around deterministic scanners, small changes, CI, and human review. Keep **at most one open PR per loop**, then feed reviewer corrections back into the skill before the next run. Increase throughput only after the loop is reliable.\n\nThe worked example is an internal RPC migration, not evidence that the pattern fits every engineering task. Even bounded loops can produce duplicate or conflicting work, and batching **three or five procedures** trades reviewability for speed.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=xIt_mTQp6mY",
    "published_at": "2026-07-25T20:41:40.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "coding"
  ],
  "topics": [
    "harness-engineering",
    "coding-agents",
    "agent-reliability"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The worked example is an internal RPC migration, not evidence that the pattern fits every engineering task. Even bounded loops can produce duplicate or conflicting work, and batching **three or five procedures** trades reviewability for speed."
  ],
  "lifecycle": "Current",
  "published_at": "2026-07-25T20:41:40.000Z",
  "modified_at": "2026-07-25T20:41:40.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/loop-engineering-from-first-principles-kyle-mistele-humanlayer-1nuq7gf",
    "json": "https://feed7.dev/p/loop-engineering-from-first-principles-kyle-mistele-humanlayer-1nuq7gf.json",
    "markdown": "https://feed7.dev/p/loop-engineering-from-first-principles-kyle-mistele-humanlayer-1nuq7gf.md"
  }
}