Q&A: designing AI features that users forgive when they are wrong
A design lead on why her team stopped chasing accuracy alone, the edit-rate metric they track instead, and the small interface changes that halved complaints.
Topic · 3 stories
Agents
Tool-using systems that take actions, and the guardrails, undo paths and review steps they need.
Prompt caching math: when it saves 75% and when it costs you more
Cached prefixes are cheap to read and slightly expensive to write. We work out the break-even hit rate, the traps that keep it at zero, and a prompt layout that helps.
Agents need an undo button before they need more autonomy
An agent that is right 97% of the time still makes dozens of wrong moves a day. Reversibility, not accuracy, makes that tolerable. An argument, with a pattern.