--- schema: 1 type: video title: >- AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j description: >- Your agent can reach your data and still get it wrong. Vector search hands it a slice, Text2SQL hands it another, and neither tells it what is actually relevant or how the pieces connect, so the answer comes back confident and wrong. Zach Blumenfeld's argument in this hands on workshop is that the missing piece is not a better model or a better query. It is context, and context comes in shapes. He builds three reusable graph shapes on top of lakehouse data with Neo4j, each answering a question the agent cannot ask a table. Trees give a table of contents, so the agent can navigate what is even there. Communities surface themes, the patterns nobody named. Paths and cycles trace connections, how entities, documents, and records actually relate. The shapes are portable to BigQuery, Databricks, or Snowflake, and you leave with the code to run them on your own data and agents. Speaker info: - https://www.linkedin.com/in/zachblumenfeld/ - https://graphacademy.neo4j.com/courses/workshop-lakehouse Timestamps: 0:00 - Introduction: context comes in shapes, not queries 6:25 - The three graph shapes to build 10:56 - Environment setup: Codespaces and Neo4j 21:47 - Schema, shared terms, and join paths 45:25 - Shape 1: a table of contents for your data (trees) 50:30 - Building the containment tree and links 59:48 - Serving the graph to the agent over MCP 1:12:21 - Q&A: naming and the containment shape 1:22:54 - Shape 2: surfacing themes with communities 1:24:24 - Community detection with Leiden 1:31:09 - Hierarchical communities and naming themes 1:43:22 - Shape 3: connections and cross links 1:50:20 - Watching the agent use outlines and themes 1:55:05 - Wrap: theme types and real time linking --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/kRkcNOsRyYg-ai-on-your-lakehouse-context-comes-in-shapes-not-queries Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/ai-on-your-lakehouse-context-comes-in-shapes-not-qu-ea16ce8ba8fc markdown: >- https://liquidgold.cc/channel/aidotengineer/video/ai-on-your-lakehouse-context-comes-in-shapes-not-qu-ea16ce8ba8fc.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T06:48:53.998Z' language: null children: [] videoId: kRkcNOsRyYg durationSeconds: 7150 publishedAt: '2026-07-23T07:00:23.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 145 endSeconds: 258 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=145' heldReason: rights - ordinal: 1 text: null startSeconds: 145 endSeconds: 258 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=145' heldReason: rights - ordinal: 2 text: null startSeconds: 269 endSeconds: 385 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=269' heldReason: rights - ordinal: 3 text: null startSeconds: 269 endSeconds: 385 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=269' heldReason: rights - ordinal: 4 text: null startSeconds: 269 endSeconds: 385 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=269' heldReason: rights - ordinal: 5 text: null startSeconds: 269 endSeconds: 385 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=269' heldReason: rights - ordinal: 6 text: null startSeconds: 396 endSeconds: 656 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=396' heldReason: rights - ordinal: 7 text: null startSeconds: 1322 endSeconds: 1454 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=1322' heldReason: rights - ordinal: 8 text: null startSeconds: 1322 endSeconds: 1454 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=1322' heldReason: rights - ordinal: 9 text: null startSeconds: 1464 endSeconds: 1558 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=1464' heldReason: rights - ordinal: 10 text: null startSeconds: 1570 endSeconds: 1683 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=1570' heldReason: rights - ordinal: 11 text: null startSeconds: 2067 endSeconds: 2183 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=2067' heldReason: rights - ordinal: 12 text: null startSeconds: 2183 endSeconds: 2281 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=2183' heldReason: rights - ordinal: 13 text: null startSeconds: 2745 endSeconds: 3030 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=2745' heldReason: rights - ordinal: 14 text: null startSeconds: 2745 endSeconds: 3030 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=2745' heldReason: rights - ordinal: 15 text: null startSeconds: 3366 endSeconds: 3376 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=3366' heldReason: rights - ordinal: 16 text: null startSeconds: 4198 endSeconds: 4315 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=4198' heldReason: rights - ordinal: 17 text: null startSeconds: 4198 endSeconds: 4315 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=4198' heldReason: rights - ordinal: 18 text: null startSeconds: 5064 endSeconds: 5074 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=5064' heldReason: rights - ordinal: 19 text: null startSeconds: 5284 endSeconds: 5367 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=5284' heldReason: rights - ordinal: 20 text: null startSeconds: 5616 endSeconds: 5731 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=5616' heldReason: rights - ordinal: 21 text: null startSeconds: 6326 endSeconds: 6462 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=6326' heldReason: rights - ordinal: 22 text: null startSeconds: 6640 endSeconds: 6908 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=6640' heldReason: rights - ordinal: 23 text: null startSeconds: 6921 endSeconds: 7150 watch: 'https://liquidgold.cc/watch/kRkcNOsRyYg?t=6921' heldReason: rights --- # AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j Your agent can reach your data and still get it wrong. Vector search hands it a slice, Text2SQL hands it another, and neither tells it what is actually relevant or how the pieces connect, so the answer comes back confident and wrong. Zach Blumenfeld's argument in this hands on workshop is that the missing piece is not a better model or a better query. It is context, and context comes in shapes. He builds three reusable graph shapes on top of lakehouse data with Neo4j, each answering a question the agent cannot ask a table. Trees give a table of contents, so the agent can navigate what is even there. Communities surface themes, the patterns nobody named. Paths and cycles trace connections, how entities, documents, and records actually relate. The shapes are portable to BigQuery, Databricks, or Snowflake, and you leave with the code to run them on your own data and agents. Speaker info: - https://www.linkedin.com/in/zachblumenfeld/ - https://graphacademy.neo4j.com/courses/workshop-lakehouse Timestamps: 0:00 - Introduction: context comes in shapes, not queries 6:25 - The three graph shapes to build 10:56 - Environment setup: Codespaces and Neo4j 21:47 - Schema, shared terms, and join paths 45:25 - Shape 1: a table of contents for your data (trees) 50:30 - Building the containment tree and links 59:48 - Serving the graph to the agent over MCP 1:12:21 - Q\&A: naming and the containment shape 1:22:54 - Shape 2: surfacing themes with communities 1:24:24 - Community detection with Leiden 1:31:09 - Hierarchical communities and naming themes 1:43:22 - Shape 3: connections and cross links 1:50:20 - Watching the agent use outlines and themes 1:55:05 - Wrap: theme types and real time linking --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/kRkcNOsRyYg-ai-on-your-lakehouse-context-comes-in-shapes-not-queries Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/ai-on-your-lakehouse-context-comes-in-shapes-not-qu-ea16ce8ba8fc · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.