{
  "schema_version": "1.0",
  "id": "s8:https://www.youtube.com/watch?v=Ib5GBkD555M",
  "slug": "harness-engineering-is-not-enough-why-software-factories-fail-dex-horthy-1tj1amt",
  "url": "https://feed7.dev/p/harness-engineering-is-not-enough-why-software-factories-fail-dex-horthy-1tj1amt",
  "title": "Harness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayer",
  "why_included": "Coding-agent loops can raise throughput without preserving maintainability. Keep human ownership of code, and use upfront alignment to make review affordable instead of trying to automate it away.",
  "summary": "The talk argues that coding models are rewarded mainly when **code runs and tests pass**, not when architecture remains easy to change. Review agents and extra loops can raise the floor, but cannot supply a missing maintainability signal.",
  "practical_implication": "Keep humans responsible for the resulting code. Use **model-assisted planning**, agree on design before implementation, and build in vertical slices so every generated change remains practical to read and test.",
  "agent_context": "The talk argues that coding models are rewarded mainly when **code runs and tests pass**, not when architecture remains easy to change. Review agents and extra loops can raise the floor, but cannot supply a missing maintainability signal.\n\nKeep humans responsible for the resulting code. Use **model-assisted planning**, agree on design before implementation, and build in vertical slices so every generated change remains practical to read and test.\n\nThere is no established benchmark here that proves how well current models preserve codebase quality. Longer-task evaluations such as **SWE Marathon**, DeepSuite, and FrontierCode may help, but model-based quality judges have their own ceiling.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=Ib5GBkD555M",
    "published_at": "2026-07-23T16:30:06.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "coding"
  ],
  "topics": [
    "harness-engineering",
    "agent-reliability",
    "agent-evals"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "There is no established benchmark here that proves how well current models preserve codebase quality. Longer-task evaluations such as **SWE Marathon**, DeepSuite, and FrontierCode may help, but model-based quality judges have their own ceiling."
  ],
  "lifecycle": "Current",
  "published_at": "2026-07-23T16:30:06.000Z",
  "modified_at": "2026-07-23T16:30:06.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/harness-engineering-is-not-enough-why-software-factories-fail-dex-horthy-1tj1amt",
    "json": "https://feed7.dev/p/harness-engineering-is-not-enough-why-software-factories-fail-dex-horthy-1tj1amt.json",
    "markdown": "https://feed7.dev/p/harness-engineering-is-not-enough-why-software-factories-fail-dex-horthy-1tj1amt.md"
  }
}