Neo4j
Neo4j is a graph database and graph intelligence company represented here through AI Engineer talks on context graphs, decision traces, graph memory, and explainable decision-aware agents [src-088].
Key facts
- Type: Graph database / graph intelligence company
- Source role: Neo4j speakers argue that agents need connected business context, previous decisions, policies, entities, events, and reasoning traces to make explainable decisions instead of merely retrieving similar documents [src-088].
- Technical pattern: The talks combine knowledge graphs, vector search, graph embeddings, Cypher queries, short-term memory, long-term memory, and reasoning memory into Context Graphs [src-088].
- Operational claim: Context graphs make agent recommendations more auditable because developers and reviewers can inspect which entities, policies, precedents, and decision traces shaped the output [src-088].
Related concepts
- Context Graphs
- Decision Traceability for Agents
- Context Engineering
- LLM Observability
- Agentic Context Management
Source references
- [src-088] AI Engineer late-May 2026 channel update (48 transcripts, 2026-05-15 to 2026-05-31)
Recommended next
Keep reading from this thread
From 494 indexed pages and articles.
- Wiki concept Context Graphs Graph-backed memory and retrieval structures that connect entities, events, policies, previous decisions, tool traces, and reasoning records so agents can make Related by neo4j
- Wiki concept Decision Traceability for Agents The requirement that important agent actions preserve enough context, reasoning, precedent, authority, and outcome data for future Related by neo4j
- Insight Recommendation Systems in Production How recommendation systems become production decisioning systems through signals, ranking, constraints, feedback loops, and experimentation Readers have engaged with this next