7 notes filed here
Chief's daily brief runs on a small local model. Getting it to behave meant moving a bullet-count limit out of the prompt and into code, then measuring what a repeat penalty setting actually cost in accuracy.
Two defects were cancelling each other out. Fixing the real one on its own would have woken a dormant guard with the wrong logic and made the page worse.
The tests for a desktop app's auto-scrolling passed the whole time the scrolling was broken: jsdom has no layout engine, so every height it reports is zero.
An agent that plans feature flag removals is useful. The rule about which flags it may never touch is what makes it safe to leave running, and what let the job move to the person who actually wants it done.
A tooling migration, some dependency bumps and a telemetry schema: none of it on a roadmap, and all of it about keeping several frontend services easy to work in.
Merged pull requests already record what you did. Turning them into a work log with an LLM is easy; the hard part is the defensive rules that stop it corrupting the vault.