I've been living inside Claude Code for the last month — 245 sessions, two agents running most days....
I scanned my own 30 days of Claude Code logs. Here's what I found (and the tool I built to do it)
Related
AI Can Find the Failure. Who Decides What the Fix Should Be?
AI can detect WCAG failures, explain them, and increasingly write the fix. But detection is not the same as deciding the fix. A real remediation example shows where the gap is, and...
Designing an Honest “Unlimited” Generative AI Product: Credits, Queues, and Fair Use
Disclosure: I am building Donatello.studio. This article describes the product and systems principles...
You can't trust assembly an AI wrote. Here's the 3-command gate.
AI assistants are confident about assembly and wrong in specific, repeatable ways. Here's a mechanical gate (assemble → disassemble → compare bytes) that catches the real failures.