The agent hands off
The agent opens a cueloop Thread and waits for your Message.
cueloop opens your agent's plan or diff in the terminal, where you comment on exact lines and send back a Message it can act on.
Your agent proposes a change and waits. You review it in the terminal and send back one Message.
The agent opens a cueloop Thread and waits for your Message.
Read it in place. Select a line, quote it, and attach a comment or a suggested change, anchored to the exact text.
Approve or ask for changes. Your comments become one clear Message for the agent.
One primitive per artifact. cueloop plan opens the latest
plan an agent proposed. cueloop diff reviews the working
tree. cueloop review pulls a pull request into the same
surface. Posting comments back is a separate, explicit step.
cueloop prototype opens a component design document.
Comment on it line by line, as you would on a plan or diff.
Press Share and cueloop copies one line. Your
teammate pastes ssh <id>@cueloop.dev and the plan
opens in their terminal, with your comments already on it.
Their notes come back to you attributed to them, over SSH the whole
way.
Comments attach to the exact lines they are about, and follow along as the plan or diff changes underneath them.
Your agent pauses for your review, then picks up your feedback and keeps going. Built into Claude Code and Codex.
Nothing to host, no account to create. cueloop runs wherever your shell does.
Share a review and everyone's comments come back in one place, attributed and intact.