•
Jul 31, 2026
An eval suite turns "the agent feels worse" into a number you can watch, before your users find the regression for you
Jul 24, 2026
The 2026-07-28 spec deletes the session, so any state your tools keep has to move somewhere the model can see it
Jul 10, 2026
An approval gate is the one checkpoint that stops an autonomous agent before it does something you can't undo
Jul 3, 2026
