You put the priority on a bet and sign it. Your agent sees it's ready to pick up.
Your call: is this worth building now?
One priority, start to finish, and your call at each step.
You put the priority on a bet and sign it. Your agent sees it's ready to pick up.
Your call: is this worth building now?
Your agent claims it before touching code, so no other agent takes it. The spec appears if there wasn't one.
Annsa writes the problem and the evidence from what customers said. Your agent writes what to build, the files to touch, and Done When: checks anyone can run. Your words are never overwritten.
Your call: is this the right thing to build?
When a call is yours, your agent asks instead of guessing, with the options and the one it would pick. It lands in Needs You.
Your call: answer once, in the app or your terminal.
Before it ships, your agent records a receipt for each Done When line it checked: a test, a link or a thread. Lines it couldn't check say so.
Your call: is it really done?
Your agent marks it shipped, with what the next spec should know. When the code reaches production, the work and its PR stay linked.
Annsa drafts a note to everyone behind the priority. You review it and send it. Cut a release to turn what shipped into a changelog.
Your call: what to say.
If customers raise it again, it comes back to you. What was decided and learned stays with it for the next agent.