Data & AI architect
Field notes on LLMs, agents, and the architecture that has to hold them.
Every agent I have built ends up doing the same thing, sooner or later: making small judgments about text. Is this support ticket about billing or about a bug? How angry is this customer? Does this paragraph actually answer the question? Is this claim true according to the document I …
I spent last week replacing an agentic pipeline with something that isn't an agent at all, and then measuring what I had actually traded away. The task is product classification: take a product description, walk down a category taxonomy (Amazon, Shopify), and land on a leaf node. The old pipeline …
Two agents meet in a park. "I've just had a complaint from a customer," says the first. "What's a customer?" asks the second. "Anyone with an account." A third agent walks over. "That's not a customer," it says. "A customer is anyone with an active subscription." The three agents pause …
Frank Coyle gave a twenty-minute talk at the AI Engineer World's Fair that has been circulating for a few weeks now, and the argument in it is simple enough to state in one sentence: agentic systems need ontologies, because LLMs are probabilistic and probabilistic systems need logical...
For a decade, gradient-boosted trees owned tabular machine learning. In the last twelve months tabular foundation models finally — and decisively — beat them on TabArena. But the lesson practitioners are drawing ("stop using trees") is almost the opposite of what the evidence supports, because...
A response to "Software Ate the World, Now Hardware Is Eating Software." The diagnosis is right — value is migrating and point software is being crushed. The prognosis is wrong. When the bottom of the stack commoditizes, value doesn't stay there. It climbs back up to the layer the thesis forgot:...
The third post in the MCP series. The first two argued when MCP wins and loses. This one looks at the terrain MCP is supposed to win on — OAuth-bound integrations — and shows why even there, the ground is more fragile than it looks.
Anyone who has spent years doing systems integration immediately understands the appeal of MCP. The dream in this field has always been the same: a clean contract between systems, where every method is described, every parameter is typed, every response is predictable. No more 80-page PDFs read...
A practical configuration for a 32 GB M5 Mac that still needs to remain usable Running large language models locally has become surprisingly practical on Apple Silicon. With a modern Mac, Ollama, and a carefully quantized GGUF model, it is possible to run models that only a short time ago …
How an MCP server turns electricity exchange data into natural conversations The Italian electricity market produces an enormous amount of data every day: hourly prices by zone, traded volumes, liquidity, the PUN (Prezzo Unico Nazionale — the national single price). Essential data for traders,...
OK. We've all been there. You're setting up a new microservice, you need a database connection string, a Keycloak client secret, an OCIR auth token — and before you know it, you're copy-pasting credentials into a .tfvars file and telling yourself "I'll fix this later". Later never comes. Until it does …
Hello, dear citizen of the free world. I’m writing while I’m in a restricted lifestyle. On Monday night Italy’s prime minister decided that the entire country would be covered by restrictions that can be summarised as follows: “I stay at home” All travel was banned unless justified …
I will ride like a gentlemen On September 24th I will ride in the Distinguished Gentlemen Ride This is me an my bike at a recent Ducati Scrambler event As a rider of a stylish Ducati Scrambler, I will join my local chapter of the DGR. It is a retro-themed …