Exploring knowledge graphs, graph theory, graph visualization, and their intersection with artificial intelligence.
graphwiz.ai is a working journal about knowledge graphs and artificial intelligence — written from hands-on projects, not summaries of other people’s work. The core question: what happens when you stop treating documents as bags of text and start treating knowledge as a graph?
The articles are organized along a few threads: AI-assisted development (agentic workflows, LLM tooling, what actually works in production), graph technology (Neo4j, GDS, GraphRAG pipelines, graph algorithms), and the self-hosted, Docker-based infrastructure both run on — documented as it was built. The GraphRAG Explorer at /graph queries the knowledge graph distilled from every article here — the site is both the source of the graph and its own best demo.
Start with the latest articles below, browse topics by tag, or look at the store if you want the distilled, deployable versions of the stacks described in the guides.
Agentic world models come in three levels. The ones that plan reliably encode the world as a graph, and the benchmark numbers are stark.
LLMs are strong inductive reasoners and weak deductive ones. The 2026 neurosymbolic agent stack pairs the model with a graph substrate it can verify and edit.
HPE says AI will close every network trouble ticket without a human in three years. The hard part is not detection — it is causal attribution over a topology.
Eight frontier models, one isolated OT lab, and a robotic arm that moved in minutes. Attack-path graphs are how defenders get ahead of agentic ICS attacks.
Deleting a row is easy. Deleting a fact that has been summarised, embedded and re-derived across a graph is where the right to be forgotten gets hard.
An agent can be wrong and still have been right at the time. Bi-temporal memory records what was true and when — but nobody benchmarks what the agent knew at time T.
LLMs are strong inductive reasoners and weak deductive ones. The 2026 neurosymbolic agent stack pairs the model with a graph substrate it can verify and edit.
Security auditing of AI agents requires traceability that traditional systems lack. This article explores a unified graph representation for LLM agents that captures every step of agent execution, enabling comprehensive security audits, compliance verification, and incident investigation.
GraphRAG has evolved from simple retrieval to sophisticated agentic context engineering. This article explores the ACE-GraphRAG framework that dynamically adapts retrieval context, explaining how it closes the representation-inference gap that plagues traditional GraphRAG implementations.