Resources
White papers on knowledge graph architecture
Longer-form arguments about the problems we keep meeting in large organisations — how a graph gets composed, governed as it changes, and served to the consumers that cannot improvise around it. Each is readable in full here, with a PDF to circulate.
AI agents · MCP
Governed context for AI agents over enterprise knowledge graphs
Why agents fail on enterprise graphs, and what a context plane has to provide before an agent can be trusted with one.
Read the paper
9 min read
Schema evolution
Version control for world models
Enterprise models change constantly, and most graph stacks have no answer. What version control looks like when the artifact is a schema rather than a codebase.
Read the paper
10 min read
Portability
Database independence for knowledge graphs
What graph database lock-in actually costs, what portability genuinely requires, and where the honest boundary of it sits.
Read the paper
8 min read