AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
Why it matters
If your AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → retrieves the right data but still answers wrong, this shows how to build graph structures — a navigable table of contents, thematic communities, and cross-entity paths — on top of your existing lakehouse and serve them to agents over MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition →, giving the model the relational context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → vector search and Text2SQL can't provide.
Key quotes
“an ontology helps something interpret and reason about the data. A semantic layer helps something understand what the consistent agreed upon terms are so it can query the data accurately.”
Zach Blumenfeld
“you can't really search for a negative. You have to search for things that are there.”
Zach Blumenfeld
“as you start adding data to it, it's almost like a bunch of pre-joined tables and everything's already interconnected”
Zach Blumenfeld
“graphs can be very useful when you start having these more global types of questions, these estate level questions that you want to ask”
Zach Blumenfeld
“it's going to go on the internet and get the Stack Overflow questions from like four or five or six years ago and it's going to give you outdated bad cipher basically”
Zach Blumenfeld
Chapters
0:00Introduction: context comes in shapes, not queries
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
