Decide what to work on next
You finished something. Instead of reading issue summaries, or scouring sticky notes and text files, ask kcap what is waiting on you, what you left unfinished, and what is new, with the reason for each. Ask from any coding agent kcap supports, or open it in the web app; the example uses Copilot CLI. Next work appears only where the workspace has it turned on; on the local edition it is off unless turned on in the server’s environment
In your agent
Section titled “In your agent”What should I work on next?The agent answers from a ranked list of things that need your attention: loose ends from your previous work, sessions you interrupted, work a teammate is waiting on, review requests, high-priority issues. Each row says why it is there
Pick one:
Take the second one. Claim the loose end and continue from where it stoppedOr decline:
Dismiss the first; that migration was abandonedA dismissed row stays dismissed until you restore it:
Show me what I've dismissed and restore the migration oneTo hand a row to a hosted agent instead of doing it yourself:
Start an agent on the second oneThe agent starts it on the machine your agent runs on, where the workspace allows agents to start agents; to pick another machine, use Work on this in the web app
In the web app
Section titled “In the web app”The What To Do Next band at the top of the dashboard shows the first rows of the same feed, and Next work at /next-work shows all of it, with your dismissed rows in their own table. Each row has the reason and the evidence behind it: the session, the work item, who is waiting. From a row you can:
- Snooze a loose end until tomorrow, three days or next week
- Dismiss a suggestion, and later Restore it from the dismissed table on Next work
- Work on this to hand the row to a hosted agent: pick the daemon and checkout, the harness and model, and the prompt the agent will receive
Dismissing, restoring and starting an agent are also sentences to your coding agent, as above. Snoozing is in the web app only
Leaving loose ends on purpose
Section titled “Leaving loose ends on purpose”The feed is only as good as what agents put in it. When you stop a session short, say so:
I'm stopping here. Leave a loose end for the retry test that still needs writingThe agent records a concrete, claimable piece of work that outlives the session and the chat