{
  "schema_version": "1.1",
  "id": "s8:https://www.youtube.com/watch?v=9dYcwOkpCE8",
  "slug": "how-we-solved-agent-building-andrew-qu-vercel-1qhqr4p",
  "url": "https://feed7.dev/p/how-we-solved-agent-building-andrew-qu-vercel-1qhqr4p",
  "title": "How We Solved Agent Building — Andrew Qu, Vercel",
  "why_included": "Vercel’s data agent improved after replacing prescriptive specialist pipelines with a filesystem, Bash and company-specific context. Eve packages that pattern as conventions.",
  "summary": "Vercel’s internal data agent began around **30% on its evals**. Moving from tightly scoped specialist agents toward a sandboxed filesystem agent with Bash, file access and company context **roughly doubled the eval score**, according to the talk.",
  "practical_implication": "Builders should test whether a capable agent can navigate domain files and a few general tools before encoding every workflow edge. Keep proprietary semantics in inspectable files and skills; use framework conventions only where they reduce runtime, deployment and channel plumbing.",
  "agent_context": "Vercel’s internal data agent began around **30% on its evals**. Moving from tightly scoped specialist agents toward a sandboxed filesystem agent with Bash, file access and company context **roughly doubled the eval score**, according to the talk.\n\nBuilders should test whether a capable agent can navigate domain files and a few general tools before encoding every workflow edge. Keep proprietary semantics in inspectable files and skills; use framework conventions only where they reduce runtime, deployment and channel plumbing.\n\nThe results describe one internal data workload rather than a published general benchmark. Eve packages the final architecture, but the talk does not establish how much improvement came from the filesystem, newer models, revised context or other simultaneous changes.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=9dYcwOkpCE8",
    "published_at": "2026-09-14T17:00:06.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "coding",
    "data"
  ],
  "topics": [
    "harness-engineering",
    "skills",
    "agent-evals"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The results describe one internal data workload rather than a published general benchmark. Eve packages the final architecture, but the talk does not establish how much improvement came from the filesystem, newer models, revised context or other simultaneous changes."
  ],
  "connected_context": {
    "meaning": "This adds unusually concrete internal eval evidence to the filesystem-agent pattern, but does not isolate which architectural change produced the gain. Against the candidates, it supports testing a general agent with inspectable domain context before building specialist pipelines, while strengthening the need for stable task contracts, trace-based diagnosis and controlled comparisons before generalizing the reported improvement.",
    "corpus_size": 778,
    "generated_at": "2026-09-15T10:06:10.015Z",
    "connections": [
      {
        "title": "Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=fjF8EKnxKCU",
        "feed7_url": "https://feed7.dev/p/agents-without-code-skills-yaml-and-filesystems-replaced-python-philipp-0t7a4s8",
        "reason": "The pull-request agent independently reaches the same minimal architecture of general tools, files and skills, while emphasizing that outcome evals remain necessary."
      },
      {
        "title": "The Unreasonable Effectiveness of Separating the Task from the Model — Maxime Rivest & Isaac Miller",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=GgLQ02aO-hs",
        "feed7_url": "https://feed7.dev/p/the-unreasonable-effectiveness-of-separating-the-task-from-the-model-max-0vu7lvy",
        "reason": "DSPy’s separation of task contracts from models and harnesses is a prerequisite for determining whether the reported eval gain came from architecture rather than simultaneous implementation changes."
      },
      {
        "title": "Improving Agents is a Data Mining Problem — Vivek Trivedy, LangChain",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=CvRngaQZQ3Y",
        "feed7_url": "https://feed7.dev/p/improving-agents-is-a-data-mining-problem-vivek-trivedy-langchain-1cgibr8",
        "reason": "Trace mining provides the next diagnostic step: recurring production failures can seed replayable evals and identify whether context, tools, orchestration or models need adjustment."
      },
      {
        "title": "The Building Blocks of GTM Orchestration — Arman Vaziri, Ramp",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=VjEP0xqTUI0",
        "feed7_url": "https://feed7.dev/p/the-building-blocks-of-gtm-orchestration-arman-vaziri-ramp-1mjpli3",
        "reason": "Ramp shows that extending this pattern across business workflows requires shared entity context and durable execution, not merely a filesystem and Bash."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-14T17:00:06.000Z",
  "modified_at": "2026-09-14T17:00:06.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/how-we-solved-agent-building-andrew-qu-vercel-1qhqr4p",
    "json": "https://feed7.dev/p/how-we-solved-agent-building-andrew-qu-vercel-1qhqr4p.json",
    "markdown": "https://feed7.dev/p/how-we-solved-agent-building-andrew-qu-vercel-1qhqr4p.md"
  }
}