Back openDesk Edu for a sovereign, open-source education — every vote counts.
Vote nowExploring 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.
Vector RAG forgets. Graph RAG remembers — which makes it a target. The attack patterns that poison knowledge graphs, why automated extraction pipelines make them easier, and the defenses that actually hold.
Query-only poisoning beats agent-memory audits with 90.7% success, and stale memory doubles agent failures. The threat model, and the defences that hold.
A fresh 760-call study of Perplexity's software recommendations shows the grounding layer is a manufactured long tail — and the two model variants agree far too often for comfort.
RAG systems are evolving rapidly, but not all RAG is created equal. This article charts the journey from naive vector search to agentic, cost-optimized knowledge integration, with practical guidance on navigating the cost-accuracy trade-off for enterprise deployments.
As AI systems evolve from simple predictive models to autonomous multi-step agents, they inherit all the technical debt of earlier AI systems — plus a new class of debt unique to agentic architecture. This article maps the root causes, symptoms, and remediation strategies.
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.
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.
GRALAN enables KGs to speak directly in the LLM's semantic space through relational tokens that preserve graph structure. No fine-tuning required — just trainable language mediation.