-
Can AI Test Thoroughly? Why the Industry Is Sleepwalking Into a QA Crisis
AI can generate a thousand tests in minutes — and that's exactly why teams are starting to mistake coverage for quality.…
-
Local Agents: Small Models, No Frameworks, One Bus
Most agent failures are scope failures — here's the minimal architecture that keeps tasks bounded, coordination simple, and the whole thing testable.…
-
Brain: Teaching Claude Code to Remember What You Already Taught It
Claude Code forgets everything when a session ends. After 30 days of building and using a session-to-knowledge pipeline, here's the architecture that makes corrections stick.…
-
What Is AI, Really? I Had to Explain It to My Daughter
My daughter asked me what AI is. Trying to explain it to her — simply, honestly — turned out to be harder than any technical interview I've ever done.…
-
From Building to Orchestrating: The SDLC Skills That Changed How I Ship
I distilled my 8-agent SDLC framework into three skills and shipped two projects in under a week. The velocity was real. So were the failure modes.…
Paul Brodner's Blog
Opinions are my own and not the views of my employer
Drawing the lines AI must follow