COMING SOON - Working on the nuget package, stay tuned! In Part 4, the recommendation became an intervention. We characterised a proposed change, applied it under an experiment and learned from the observed response. An email could be a candidate in the same…
The “mind control” in the title is a joke about a familiar ambition: put the right thing in front of someone at the right moment and change what they do next. Most of us have ignored enough perfectly timed marketing emails to know how unreliable that ambition…
In Part 2, we turned an entity's characterisation into recommendations. We could watch a session change, find eligible products, and explain which representations contributed to the ranking. Now we want to use that history to answer a more useful business…
“How do I vectorise this?” This is an optional bridge between Part 1 and Part 2. It focuses on producing coordinates for properties we cannot read directly from a database field or event counter. Take a voice message. Is this message aggressive? The transcript…
In Part 1, we looked at how to characterise an entity. We chose observations, encoded the relationships we cared about, and used vectors and centroids to summarise what we had seen. That entity could be a shopper, a service or a device. Now we can ask the next…
You buy a kettle, and the shop spends the next fortnight recommending kettles. You browse a birthday present, and suddenly your entire personality is scented candles. Meanwhile, the thing you actually came back to find is three pages down. Recommendation…
In the previous part, we checked whether generated prose contains an answer and whether evidence supports its claims. We kept those checks separate from whether the answer reads well. Now suppose those checks keep finding the same mistakes: assistance becomes…
How do we check that generated prose contains the right information, rather than merely sounding like a good answer? Ask an agent for a refund status when the authoritative tool says pending. “Your refund is complete” answers the question but contradicts the…
lucidRESUME needs to turn one complete career transcript into distinct, credible résumés. Select an applied-AI job: foreground agent architecture, evaluation and tool controls. Select a database job: foreground queries and performance. An early version found…
Deep Research without Deep Pockets. When "Deep Research" landed in the premium AI tools, I was curious: what is this, actually? So I pulled it apart. And once I understood the architecture, I realised I'd already built most of it. DoomSummarizer leverages a…