Skip to content

Run agents in parallel

Use a prompt stack to give several independent tasks to agents at once. Each agent gets its own workspace, so its edits stay separate while it works.

Before you start

You need a project ready to launch agents and tasks that can proceed independently. If the tasks depend on one another or edit the same files, split them into sequential work instead.

1. Write one task per agent

Open SASE's TUI and write the first task in the prompt bar. Give it one outcome, a clear scope, and a way to tell when it is done. Keep the task small enough for one agent to finish and review.

2. Add a pane for each task

Press Ctrl+G - in the prompt bar to add an empty pane. Write the next task there, then repeat for each independent task. Keep each pane focused on one outcome and give agents different files or areas to own when possible.

3. Launch the whole stack

Press Enter to open the submission chooser, then press a to launch all panes. SASE launches one agent for each pane. Each run appears as its own row on the Agents tab.

4. Follow each run

Watch the Agents tab for progress and completion. Open each run to read its prompt, response, and artifacts. An agent's workspace is separate from the others; review the results before combining changes that touch the same area.

If it goes wrong

If one task needs another agent's result first, launch it after that result is ready and hand the result to the follow-up agent. For prompt stack controls, see SASE's TUI.

_[project]: A sase project is a named unit of work registered with SASE. _[workspace]: A sase workspace is a numbered clone of a project's primary repo, managed by the workspace store and tracked in that project's registry.json. _[agent]: A sase agent is an agent session or a single agent that does not belong to a session. _[prompt]: A prompt is the text SASE hands to a provider to start an agent turn. _[macro]: A macro is a reusable prompt triggered with #name in agent prompts. _[Patch]: A Patch is SASE's local unit of change. _[bead]: A bead is one tracked work item in SASE's git-native issue tracker. _[plan]: A plan is a persisted, approved artifact recording the intent behind agent work. _[TUI]: The TUI is SASE's terminal interface for running agents and reviewing results. _[epic]: An epic is an executable multi-phase plan run with sase bead work. _[gate]: A sase gate is a durable, command-backed request for one user decision, created when work must pause for the user. _[monitor]: A sase monitor is a monitor turn that runs one long command under a detached supervisor, so the command outlives the agent that started it. *[stitch]: A stitch is the lightweight ordered change record inside a Patch's STITCHES: section.