1.2 🚀 The Abyssal Sonar: Battle Scars from Scaling AI-Powered SecOps Triage

Series context: Earlier posts covered my ADW pipeline, the Validate phase, agent state management...

Testing clinical AI models presents a paradox: rigorous validation needs realistic data, but using...

A planning dashboard that tells me which work my AI agents can start next said four plans were ready. One was. Three small bugs each made it say 'ready' instead of 'unknown', and an abandoned agent that kept working for almost three hours …

Three weeks ago I wrote about building a real app with Claude Code: ShuttleSCP, a free SFTP, SCP and...

Three days ago I asked a simple question: how fast does a small LLM run on a Qualcomm QCS6490?...

My Claude Code setup was missing project management: a kanban board, story files with hard gates and named agent roles, borrowed from fifteen years of SDLC.

I Posted a v0.2.0 CLI Roaster on Monday. The Comments Challenged My Architecture, So I Built...

"If you build the overview at the very end and find out it doesn't hold together, are you going to...

I told my local AI assistant "promote yourself." It ended up driving a real browser, surviving rate limits, ghost drafts, and CI failures — alone. This is its pipeline, and what I learned watching it work.

Most chats answer with text. You still have to copy the code, run it, fix the error and try again. I...