Practical Fun with Personal Agents: Staying on Top of Schoolwork Without Fighting the PortalOct 8, 2026·9 min read
Inside Design Studio: Giving Your Terminal a Tasteful Visual DirectorHow We Built an In-Browser Atelier That Translates Raw Engineering Gut Feedback into World-Class DesignOct 13, 2026·15 min read
The Product vs. The Work: Managing Engineering Exhaust in the Age of AI Coding AgentsOct 5, 2026·11 min read
The Clockwork Candidate: What Happens When Inbound Costs NothingThree applications, seventy minutes apart, identical echoes. Notes on the industrialization of synthetic hiring.Oct 2, 2026·6 min read
The Claudish Tax: What Four Months of Opus Prose Cost Us, and How to Sweep It OutA few weeks ago, I wrote about forcing Claude Code to speak human. Last week, I wrote about ripping AI ceremony out of a codebase. This memo is the follow-up, because the problem is far wider and moreSep 30, 2026·12 min read
No. You Don't Need Cryptographic Hashing.I was asked to do a design review of a portion of a system recently, and I opened a decision document proposing a dictionary called RELEASE_FINGERPRINTS. Every prompt file in the project was to have iSep 27, 2026·19 min read
How to Corral Gemini for Agentic CodingGemini has developed a bit of a reputation in the multi-agent space. I recently heard someone refer to it as the "idiot in the room" when it comes to long-term agentic coding. That is both unfair and Sep 25, 2026·4 min read
Forcing Claude Code to Speak HumanAnyone who uses Claude for serious research and development eventually hits the same wall: the way it speaks. If I have to read one more time that I am "right to push back on that," or that we need toSep 24, 2026·5 min read
Part 4: Real-Time Pipeline DiagnosticsCalibrated Flake vs. Regression Triage in Automated Builds Sep 23, 2026·5 min read
