← back
Context Engineering: Connecting the Dots with Graphs — Stephen Chin, Neo4j
Takeaway
Layer knowledge graphs on top of vector RAG so LLMs can traverse relationships, retrieve community structure and maintain typed long/short-term memory — not just semantic neighbors.
Summary
- Context engineering = treating prompt engineering, RAG, memory and structured output as one discipline of feeding the LLM the right signal vs noise
- Knowledge graphs (nodes, relationships, properties with embeddings) act as a structured complement to LLMs' language reasoning and creativity
- GraphRAG augments retrieval with graph queries — pulling nodes, communities and relationships gives more relevant context than pure vector similarity
- Memory architecture: short-term memory compresses current task info while long-term memory captures episodic/semantic/procedural knowledge to fill gaps and reduce hallucinations
- Recommends DSPy/BAML for dynamic prompting on top of structured graph context to improve reliability and explainability
graph-ragknowledge-graphsneo4j
Original description
AI systems need more than intelligence; they need context. Without it, even the most advanced models can misinterpret information, lose track of details, or arrive at conclusions that don’t hold up. Context engineering is emerging as a discipline that shapes how AI perceives, recalls, and reasons about information. This talk will explore how context provides the foundation for reasoning, problem solving, and explainability in AI. We will look at techniques such as connected memory, contextual retrieval, and graph-based knowledge representation that give large language models a more reliable way to connect information and draw logical conclusions. Attendees will come away with a practical understanding of how to design effective context pipelines that align AI with real-world knowledge and user intent, and why context engineering is becoming a central part of building trustworthy and impactful AI systems. Stephen Chin is VP of Developer Relations at Neo4j, conference chair of the LF AI & Data Foundation, and author of numerous titles including the upcoming GraphRAG: The Definitive Guide for O'Reilly. He has given keynotes and main stage talks at numerous conferences around the world including AI Engineer Summit, AI DevSummit, Devoxx, DevNexus, JNation, JavaOne, Shift, Joker, swampUP, and GIDS. Stephen is an avid motorcyclist who has done evangelism tours in Europe, Japan, and Brazil, interviewing developers in their natural habitat. When he is not traveling, he enjoys teaching kids how to do AI, embedded, and robot programming together with his daughters. --- Socials: - LinkedIn: https://linkedin.com/in/steveonjava - X (Twitter): https://x.com/steveonjava - GitHub: https://github.com/steveonjava - Company: Neo4j (https://neo4j.com)