A background agent completes 90% of a task. The remaining 10% needs human judgment - a nuance the agent missed, a decision that requires context the agent doesn't have. If the handoff from "agent working" to "human editing" is clunky, you've just negated the benefit of automation. The transition is a design problem.
The "assistant" model -sitting in a sidebar, watching an agent work, ping-ponging back and forth -optimizes for the wrong thing. As models become capable of autonomous work for 45 minutes or more, the human becomes the bottleneck. The future of agent tooling isn't a better sidebar. It's a factory: spawn multiple agents, let them run, check in periodically.
How do you know what to build when your users are constantly adapting your product? When AI agents enable power users to "abuse" features for unintended purposes, that behavior isn't noise -it's signal. Latent demand is the idea that you can discover real product needs by building extensible, hackable systems and watching what people actually do.