Deep dives into GraphRAG, knowledge graphs, AI architectures and the future of enterprise knowledge systems.
The effort did not disappear when I stopped writing code by hand — it moved to the front. A tour of how I actually work in Cursor, and why delegating the keystrokes raises the bar rather than lowering it.
Read article →Every AI system — from a single chatbot to a multi-agent orchestration — stands on the same footing: secure data foundations. Here is how to think about the data your models touch, and why the only controls you can trust live outside the model.
Read article →What if every website could answer questions from an AI agent instantly, without sending content to a third party? Dotty is a lightweight open protocol that moves the expensive work offline.
Read article →A deep dive into the memory architecture that turns every customer interaction into organisational intelligence — from verbatim session logs to cross-user reflections.
Read article →A deep technical comparison of graph-based versus pure vector retrieval — and why the structural relationships in knowledge graphs matter for complex, multi-hop queries.
Read article →How to combine the reasoning power of frontier LLMs with the precision and recency of your organisation's proprietary knowledge — without hallucination.
Read article →A survey of the latest embedding techniques for knowledge graphs — from TransE to RotatE to the newest transformer-based approaches — and what they mean for practitioners.
Read article →