Opening Keynote: Exploring Context Graphs: From Data to Decisions - Extended Version
summary
Panel argues that context graphs are a concrete layer that capture decision traces (agent tool calls, outcomes, why a deal closed) and stitch them into a reusable fabric; demos include a Neo4j financial‑services app and a 20‑domain create context graph generator that pulls Google Workspace, Linear and code discussions into a graph, uses structural embeddings for discovery, implements trust‑scoring and governance, and proves agents can earn authority when memory and auditability work end‑to‑end.
AI-written summary · about
chapters (10)
- 0:00Introduction to panel
- 1:36Defining context graphs
- 5:05Infrastructure and trust
- 7:21Enterprise adoption signals
- 10:29Building context graph tools
- 14:28Lessons and challenges
- 19:25Local vs global graphs
- 26:04Ontologies in AI
- 33:59Neo4j and startup growth
- 37:38Advice and final thoughts
related talks
56mConnecting the Dots with Context Graphs
23mConnecting the Dots With Context Graphs
18mConnecting the Dots with Context Graphs
29mHow to Structure Context to Make Your Agents Smarter
38mSearch is Back: Solving the "Context Crisis" for AI Agents
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI
15mUnderstanding Context Engineering for Agentic Systems
12mTopology Over Predictions: Using Graph Context to Drive Real-Time Lending Decisions