{
  "schema_version": "1.0",
  "id": "s8:https://www.youtube.com/watch?v=CgsWxRUY5Eo",
  "slug": "ai-agents-for-performance-ship-faster-pay-less-rajat-shah-netflix-1c2tvq2",
  "url": "https://feed7.dev/p/ai-agents-for-performance-ship-faster-pay-less-rajat-shah-netflix-1c2tvq2",
  "title": "AI Agents for Performance: Ship Faster, Pay Less — Rajat Shah, Netflix",
  "why_included": "Netflix’s performance-agent playbook feeds production profiles and exact deployed code to agents, then relies on canaries and engineers to validate proposed optimizations.",
  "summary": "Netflix found a hidden **quadratic-time pattern** by giving an agent call-stack profiling data, then locating the matching code at the production commit. The proposed workflow turns profiles into candidate fixes instead of relying only on manual flame-graph inspection.",
  "practical_implication": "Build a shared Git-backed catalog of observed performance patterns, and let coding or review agents consult it before inefficient code lands. A **stateful catalog plus a stateless LLM** can spread production lessons across services without requiring a vector database.",
  "agent_context": "Netflix found a hidden **quadratic-time pattern** by giving an agent call-stack profiling data, then locating the matching code at the production commit. The proposed workflow turns profiles into candidate fixes instead of relying only on manual flame-graph inspection.\n\nBuild a shared Git-backed catalog of observed performance patterns, and let coding or review agents consult it before inefficient code lands. A **stateful catalog plus a stateless LLM** can spread production lessons across services without requiring a vector database.\n\nTreat the profiler as an estimate and the **canary as ground truth**; error rates and an engineer’s decision remain release gates. The talk favors fixed, level-two orchestration because greater autonomy demands more evaluation, sandboxing, and prompt-injection defenses.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=CgsWxRUY5Eo",
    "published_at": "2026-07-28T00:59:04.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "coding"
  ],
  "topics": [
    "harness-engineering",
    "agent-memory",
    "agent-reliability"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Treat the profiler as an estimate and the **canary as ground truth**; error rates and an engineer’s decision remain release gates. The talk favors fixed, level-two orchestration because greater autonomy demands more evaluation, sandboxing, and prompt-injection defenses."
  ],
  "lifecycle": "Current",
  "published_at": "2026-07-28T00:59:04.000Z",
  "modified_at": "2026-07-28T00:59:04.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/ai-agents-for-performance-ship-faster-pay-less-rajat-shah-netflix-1c2tvq2",
    "json": "https://feed7.dev/p/ai-agents-for-performance-ship-faster-pay-less-rajat-shah-netflix-1c2tvq2.json",
    "markdown": "https://feed7.dev/p/ai-agents-for-performance-ship-faster-pay-less-rajat-shah-netflix-1c2tvq2.md"
  }
}