---
title: "AI on Your Lakehouse: Context Comes in Shapes, Not Queries"
category: "talks"
date: "2026-06-29"
time: "9:00am-11:00am"
track: "Track 2"
room: "Track 2"
speakers: ["Zach Blumenfeld"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Track 2"
scheduleRoom: "Track 2"
scheduleLabels: ["Track 2", "Track 2", "sponsor", "confirmed"]
---
# AI on Your Lakehouse: Context Comes in Shapes, Not Queries

## Conference Context
- Date/time: 2026-06-29 · 9:00am-11:00am
- Track/room: Track 2 · Track 2
- Speaker(s): Zach Blumenfeld
- Session type/status: sponsor · confirmed

- Track: Track 2
- Room: Track 2
- Session type: sponsor
- Status: confirmed

## Session Description
Your agent can reach your data but still can't use it reliably: vector search and Text2SQL each hand it a slice, but not the view to know what's truly relevant and how to connect the right info. Without that, answers come back confident but wrong, and agent decisions cannot be trusted. The problem isn't caused by a bad model or bad query, but rather a lack of context, and thinking in terms of shapes is what cracks it. In this hands-on session, you'll learn how to build three reusable graph shapes from your lakehouse data using Neo4j, so your agent can navigate and view the right context to answer and act accurately: - Table of Contents (Trees) — navigate what's there - Themes (Communities) — surface patterns nobody named - Connections (Paths & Cycles) — trace how entities, documents, and records relate Portable to BigQuery, Databricks, Snowflake, or anywhere. You'll leave with real, practical techniques and the code to run with your own data and agents.

## Media Evidence
[Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j](https://www.youtube.com/watch?v=B9h9ovW5H9U) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

- [[youtube-B9h9ovW5H9U-transcript]] — full cached transcript markdown for the related YouTube source.

- Source video: `youtube-B9h9ovW5H9U`
- Slide deck: [[youtube-B9h9ovW5H9U-dense-slides|Dense Slides: Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j]] — 1 visible slide image(s); 1 HTML recreation(s).
![[assets/dense-slides/B9h9ovW5H9U/slide-001.jpg]]
- Additional slide evidence: [[youtube-B9h9ovW5H9U-slides|Slides: Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j]], [[youtube-B9h9ovW5H9U-reconstructed-slides|Reconstructed Slides: Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j]]
- Slide-derived themes for `youtube-B9h9ovW5H9U`: engineering, future.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
- `youtube-B9h9ovW5H9U` — 2,859 transcript words; 1 slide-derived text signals
- Transcript signals for `youtube-B9h9ovW5H9U`: graph, context, data, create, traces, back, little, decision.
- Slide-derived themes for `youtube-B9h9ovW5H9U`: engineering, future.
- Evidence links for `youtube-B9h9ovW5H9U`: [[youtube-B9h9ovW5H9U]], [[youtube-B9h9ovW5H9U-transcript]], [[youtube-B9h9ovW5H9U-slides]], [[youtube-B9h9ovW5H9U-dense-slides]], [[youtube-B9h9ovW5H9U-reconstructed-slides]]

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Cached at `raw/sources/youtube-transcripts/B9h9ovW5H9U.txt` (2,859 words).

## People
- [[zach-blumenfeld]]

## Supporting Slides
- [[youtube-B9h9ovW5H9U-slides]] — extracted from the related public AI Engineer video.

## Slide Evidence
- Slide-only cropped deck: [[youtube-B9h9ovW5H9U-dense-slides]] (1 viable slide images).
- Related slide/OCR pages:
- [[youtube-B9h9ovW5H9U-dense-slides]]
- [[youtube-B9h9ovW5H9U-reconstructed-slides]]
- [[youtube-B9h9ovW5H9U-slides]]
- Slide-derived terms: `context`, `graph`, `engineering`, `claude`, `future`, `graphs`, `knowledge`, `base`, `engineer`, `decision`, `relationships`, `neo4j`, `alengineer`, `information`, `required`, `jessica`, `backend`, `frontend`

## Attendance Visibility
No high-confidence attendance icon signal is shown for this talk. The sampled video evidence was either low confidence, source-proxy-only, or did not expose a clear audience view.

## Synthesis
### Synthesized Breakdown
So, my name is Zach. Uh I work for Neo4j. We're a graph intelligence company. You can think of us like a knowledge layer graph database at the core.

### Speaker And Company Context
- [[zach-blumenfeld|Zach Blumenfeld]] — AI Research Engineer at [[neo4j|Neo4j]].

### Topics Covered
- [[agent-security]]
- [[agentic-search]]
- [[coding-agents]]
- [[mcp]]

### Derived Links And Source Material
- [[youtube-B9h9ovW5H9U-transcript]] — transcript markdown; source cache `raw/sources/youtube-transcripts/B9h9ovW5H9U.txt` (2,859 words).
- [[youtube-B9h9ovW5H9U]] — related YouTube source page.
- [[youtube-B9h9ovW5H9U-slides]] — slide evidence.
- [[youtube-B9h9ovW5H9U-reconstructed-slides]] — slide evidence.
- [[youtube-B9h9ovW5H9U-dense-slides]] — slide evidence.

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis uses the official schedule plus cached video transcripts. Official AI Engineer World's Fair San Francisco 2026 livestreams and cut videos are primary event video sources for transcript/slide evidence; external, historical, or speaker-matched videos remain supporting context unless manually verified as exact official event recordings.