Act, Confirm, or Stop? Smarter behavior for AI assistants, wearables & robots — Amit Desai, Roku
An assistant can reduce user pain without improving model accuracy by choosing when to act, confirm, or stop. Optimize those decisions against the cost of each failure mode, not intuition.
The example holds recognition accuracy at **79%** and assigns user-cost estimates to wrong actions, stops, and confirmations. Immediate action costs 2.1 points per turn; a guessed 65% stop threshold lowers that to 1.904 but is not optimal.
Model act, confirm, and stop as separate decisions under uncertainty. With the stated costs, optimization selects **41% and 49% thresholds** and lowers the modeled cost to **1.464 points per turn**, without changing the underlying predictions.
The example holds recognition accuracy at **79%** and assigns user-cost estimates to wrong actions, stops, and confirmations. Immediate action costs 2.1 points per turn; a guessed 65% stop threshold lowers that to 1.904 but is not optimal. Model act, confirm, and stop as separate decisions under uncertainty. With the stated costs, optimization selects **41% and 49% thresholds** and lowers the modeled cost to **1.464 points per turn**, without changing the underlying predictions. Those thresholds are not portable defaults. The cost values are heuristics, and they change with modality, recovery time, and consequence; sending an email or moving a robot warrants different penalties than playing a song.
This isolates runtime decision policy as a reliability lever: unchanged predictions can cause less user harm when acting, confirming, and stopping are optimized separately. It makes safe interruption quantitative rather than intuitive, while narrowing the result to chosen cost assumptions that must be recalibrated for each interface and consequence profile.