7) Multi-agent design. I loved the design of Cove (they were the acquired by Microsoft). It was more of a whiteboard than tabs or chat threa…

7. Multi-agent design. I loved the design of Cove (they were the acquired by Microsoft). It was more of a whiteboard than tabs or chat threads. I don’t think we’ve cracked the right UI for managing agents quite yet (even if we’re just talking to one main CoS and that agent is delegating down the reporting line). 8) Discoverability. This is a mess on all platforms. I like Claude code surfacing tips while it’s thinking and working for you. But unless you're scrolling X for hours a day, or constantly checking in on the AI labs' tweets and documentation, or learning from people who are doing that (like the mastermind I'm running), you’ll never learn the really advanced features and tricks. It feels unsolvable without AI as the surfacer. 9) Model selection. I realize it is just a dropdown, but the vast majority of AI users don’t know the model differences and tradeoffs. They’ll say “I want the fastest answers possible” and then when a response is low quality, their instinct isn’t to push back or switch to a more powerful AI model, they assume AI cannot do that task. The auto-selectors don’t seem to fully solve this problem either.

Source: Allie K. Miller (X) | 2026-04-26