It's hard to find (or know) the line between necessary scope / work and "nice to have". You want to be on an aware path (Product should know current view of the full potential scope) but delivering on minimal incremental scope to drive value. However, in doing
Stream of consciousness post on a busy weekend (forgive me). I was listening to Eric Jorgenson's new Book of Elon and Elon's view on "reasoning by analogy" stood out to me. The concept is familiar and pretty obvious but I thought specifically framing it
Post mostly written by Claude - but it's a good relevant topic for those building agentic systems. One of the most common questions I get from teams building AI-powered knowledge systems is deceptively simple: Why do I need a retrieval step at all? Can't I just
Note: This is just stream of consciousness (dictated) as this is a post on a short-term topic that'll likely just get taken down at some point. I've been building with Claude Code, like many have, and thought that the recent every posts and writing on
I've been spending spare time working on a startup to improve how marketing materials in regulated industries are substantiated. I'm writing while doing so to do some version of "build in public", invite discovery and conversation, and just share why it's fun
Some pretty scattered thoughts this morning that I'll edit into real posts at some point (maybe..). In thinking about this I'm thinking in the context of one knowledge worker and their daily workflows. That's vague and specifics matter but let's hold it
What I'm building In my nights and weekends, I'm exploring a problem in regulated content creation. When companies in highly regulated industries (pharma, finance, etc.) create content, every factual claim needs to be substantiated with a citation. This sounds simple, but the workflow is brutal: * Writers