An AI app can respond quickly and still leave people waiting. Streaming an answer doesn’t help much if the interface freezes or a follow-up message sits behind a long-running task.

Drawing on lessons from Lovable, we’ll improve an intentionally frustrating AI app and measure what changes. We’ll look at responsive interfaces, background work, and matching the model to the task, while letting users steer the agent before it finishes. You’ll leave with a practical approach to reducing unnecessary waits and keeping people involved while the work happens.

Talk · 40 min