{
  "schema_version": "1.0",
  "id": "s8:https://www.youtube.com/watch?v=kRkcNOsRyYg",
  "slug": "ai-on-your-lakehouse-context-comes-in-shapes-not-queries-zach-blumenfeld-0r4s9u5",
  "url": "https://feed7.dev/p/ai-on-your-lakehouse-context-comes-in-shapes-not-queries-zach-blumenfeld-0r4s9u5",
  "title": "AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j",
  "why_included": "Graph-shaped context can expose relationships and document structure that vector search or Text-to-SQL misses. Treat it as an additional retrieval surface, then benchmark it against your own data.",
  "summary": "The workshop builds graph representations over lakehouse tables and documents, letting an agent inspect metadata, traverse linked document hierarchies, and detect document communities. Tool calls are exposed through **MCP history** in the demonstrated setup.",
  "practical_implication": "Give data agents several context shapes rather than one universal query path. Use a metadata graph to plan SQL, linked views for document neighborhoods, and **community detection** when thematic grouping helps investigation.",
  "agent_context": "The workshop builds graph representations over lakehouse tables and documents, letting an agent inspect metadata, traverse linked document hierarchies, and detect document communities. Tool calls are exposed through **MCP history** in the demonstrated setup.\n\nGive data agents several context shapes rather than one universal query path. Use a metadata graph to plan SQL, linked views for document neighborhoods, and **community detection** when thematic grouping helps investigation.\n\nThe workshop reports **no accuracy benchmark** for the demonstrated system. Its structured and unstructured graphs are also unlinked, leaving the agent to join extracted identifiers at runtime unless builders add deterministic connections.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=kRkcNOsRyYg",
    "published_at": "2026-07-23T07:00:23.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "context",
  "domains": [
    "data"
  ],
  "topics": [
    "context-engineering",
    "retrieval",
    "mcp"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The workshop reports **no accuracy benchmark** for the demonstrated system. Its structured and unstructured graphs are also unlinked, leaving the agent to join extracted identifiers at runtime unless builders add deterministic connections."
  ],
  "lifecycle": "Current",
  "published_at": "2026-07-23T07:00:23.000Z",
  "modified_at": "2026-07-23T07:00:23.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/ai-on-your-lakehouse-context-comes-in-shapes-not-queries-zach-blumenfeld-0r4s9u5",
    "json": "https://feed7.dev/p/ai-on-your-lakehouse-context-comes-in-shapes-not-queries-zach-blumenfeld-0r4s9u5.json",
    "markdown": "https://feed7.dev/p/ai-on-your-lakehouse-context-comes-in-shapes-not-queries-zach-blumenfeld-0r4s9u5.md"
  }
}