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…
NOTE: This is not a conventional blog article. It is a technical spec written for a concrete feature in lucidRAG. I iteratively feed this document to code-focused LLMs during development to reason about trade-offs, validate assumptions, and converge on a…
I built StyloFlow because I kept writing the same pattern over and over: components that react to what happened before, emit confidence scores, and sometimes need to escalate to more expensive analysis. Existing workflow engines wanted me to think in terms of…
This is Part 5 of the DocSummarizer series, and it's also the culmination of the GraphRAG series and Semantic Search series. We're combining everything into a deployable web application. 🚨🚨 PREVIEW ARTICLE 🚨🚨 Still working out some kinks and adding…
What This Series Builds This series builds a working ecommerce system that proves you can have sophisticated customer intelligence without storing personal information. What We Build How It Works Semantic segmentation Vector embeddings group similar interests…
In Part 1 we covered the philosophy: transparent segmentation without PII. Part 2 covers session profiles, signals, and segment definitions. But first: how do you validate any of this without ever touching real customer data? For this series I generate a…
In Part 1 we covered the philosophy and series overview. In Part 1.1 we built the sample data generator. Now let's build the core system. This part focuses on: Zero-PII profile architecture - Ephemeral sessions vs persistent profiles Signals and weights - What…