Sending a task from my phone is worthwhile only if the agent does its share of finding context. If I have to prepare a dossier on a tiny screen, the convenience is gone before work begins. I want to send a clear reference and get on with my day while the task moves within that request.
Dispatch appeared in Anthropic's March 2026 computer use announcement, with the promise of starting tasks from a phone and executing them on a computer. What interests me is the continuity between those screens: what happens after I hit send away from my desk.
I expect an agent to find the information it needs before sending questions back to me, and I don't want to hand it the context of every project I have. Both fit the same request: research what the task needs, and only that. If the task points to a change already described in the project, asking me again for what is written there just transfers the research to the person typing with a thumb.
A question about my intention has a different value. If two projects are plausible and there is no sufficient clue, a short question helps. I want that distinction in practice: the agent should recognize when my decision is missing and when it needs to open a document.
Sending all context everywhere also bothers me. Decisions from another project can end up in a task where they have no business being. I prefer relevant references and a search guided by the request. I need to understand why information entered the execution, especially when the conversation starts away from the computer.
Back at my desk, I want the result attached to the request I sent. I also want to see what remains without reconstructing an entire conversation. My next criterion for this kind of tool is a short request with accessible supporting material: watch what it finds independently and which questions come back.