Home / Writing WRITING Writing A weekly long-form article on Medium, plus shorter takes and project notes on LinkedIn: what works, what does not, and what teams get wrong on their first knowledge-graph project.
Medium ↗ LONG-FORM · WEEKLY Long-form articles on Neo4j, GraphRAG, and applied graph-AI. RECENT ARTICLES SEP 14, 2026 Parser First, LLM Second: Building a 10-K Knowledge Graph in Neo4j Five companies, five years, 25 SEC filings - and a rule that the numbers never touch a language model. The build behind the 10-K graph, from raw filings to chat. SEP 1, 2026 How I Test a Knowledge Graph Competency questions and invariants turn "the graph looks right" into something you can verify - shown on a 10-K filings graph anyone can read. AUG 19, 2026 Do Knowledge Graphs Fail as Agent Memory? What Two 2026 Benchmarks Actually Show Two studies say graph memory loses on cost and accuracy. A closer read - plus the memory tools worth trying, for coders and non-coders alike. AUG 13, 2026 How Do You Know That? Adding a Provenance Layer to a Supply-Chain Knowledge Graph in Neo4j A traceability graph says where a batch came from. It usually can't say how you know - and that gap is a modeling choice, not a tooling problem. AUG 11, 2026 The Supplier That Stops Everything: Finding Supply Chain Chokepoints with Neo4j and GDS Toyota paused hybrid SUV orders over a part four tiers deep. BASF shut ammonia plants that fed four industries. Both are the same graph problem. AUG 7, 2026 Beef Lasagne, Five Countries, One Graph: The Horsemeat Scandal and Neo4j A frozen lasagne crossed five countries before anyone could name what was in it. The fix wasn't more paperwork - it was modelling the supply chain. AUG 1, 2026 From Spreadsheet to Substitution Engine: Building an Agricultural Knowledge Graph in Neo4j, Layer by Layer Build an agricultural knowledge graph one public data source at a time, and watch the questions it can answer get more interesting with every layer. JUL 22, 2026 Agriculture Already Has Its Ontologies. The Knowledge Graph Is Where They Expire. The ontology is the easy part. Keeping its facts from going stale is the whole job. LinkedIn ↗ SHORT TAKES Shorter takes and project notes from ongoing graph work.