AI systems need more than intelligence; they need context that persists. Without it, even strong models can misinterpret information, lose decision rationale, or repeat the same mistakes. Context Graphs have emerged as a practical pattern for agentic AI: a living graph that captures not only what was retrieved or known, but how context led to actions through tool calls, constraints, policies, and outcomes, stitched across entities and time so precedent becomes searchable.

This talk explores context engineering as the discipline of designing that context layer, and shows how context graphs complement retrieval by enabling multi-hop, structured context assembly (building on GraphRAG-style hierarchical summaries) while improving explainability and evaluation. Attendees will leave with a practical understanding of how to build context pipelines that combine contextual retrieval with persistent memory and provenance, and why context graphs are becoming central to trustworthy, enterprise-ready AI systems.

Jfokus

A conference talk by Stephen Chin (VP of Developer Relations at Neo4j) covering context graphs as a way to improve AI system quality. The talk explains the shift from prompt engineering to context engineering, introduces knowledge graphs and graph RAG as superior alternatives to vector-only RAG, and demonstrates how combining knowledge graphs with MCP tools enables AI agents to pull from multiple data sources for more accurate, explainable, and auditable results. Three live demos are shown: Neo4j's LLM Graph Builder for security vulnerability analysis, Claude Code with a Neo4j Cypher MCP server, and a full context graph system for financial decision-making (credit limit approvals). Key topics include short vs. long-term agent memory, community detection algorithms (Louvain), graph schema design best practices, and how LLMs can both build and query knowledge graphs.

Connecting the Dots with Context Graphs, by Stephen Chin