Thinking from the deep end.
Field notes on building serious systems, data, machine learning, AI agents and the platforms that carry them.
IoT: the nervous system behind real-world action
Sensors do not just fill dashboards. They feed the data that lets people, software agents and robots act in the physical world, safely and on time.
Why your data foundations decide whether AI succeeds
Most failed AI initiatives are not model failures, they are data failures. Here is how to build the foundation that makes everything downstream possible.
Putting AI agents into production without losing control
Autonomous agents are moving from demo to dependency. Shipping them responsibly is an engineering discipline, grounding, guardrails, evaluation and oversight.
Modernising a platform without stopping the business
Legacy modernisation fails when it becomes a big-bang rewrite. The alternative is incremental, reversible, and keeps the lights on the whole way.
From notebook to production: what MLOps really means
A model in a notebook is a hypothesis. A model in production is a system. MLOps is the discipline that gets you reliably from one to the other.
Build versus buy: how to decide on your AI platform
Build, buy or assemble? A clear framework for deciding where to spend your engineering effort on AI, and where a vendor is simply the better call.
Real-time or batch? Choosing the right data architecture
Streaming is not automatically better than batch. A practical way to decide how fresh your data really needs to be, and to avoid paying for latency you never use.
Robotics and the automation continuum
Software agents and physical robots are two ends of one continuum. The same discipline that makes an agent trustworthy is what makes automation safe at the physical edge.
Have something worth building well?
Whether you are starting from a blank page or rescuing something that has outgrown its foundations, let's talk about what good looks like.