Skip to content

Hand a result to another agent

Use an artifact reference to give a follow-up agent the result it needs to continue the work.

Before you start

You need the completed agent run and a specific next task. Decide whether the next agent needs the earlier conversation, a file, a Patch, or another recorded artifact.

1. Copy a reference to the result

On the Agents tab, focus the completed run and press a to open its artifacts. Select the result, press % to open the Copy as… palette, and choose its prompt-reference form. For the whole agent conversation, use an agent reference such as @agent:<name>; replace <name> with the selected run's name.

2. Put the reference in a focused prompt

Start a new agent prompt and paste the reference. State what the next agent should do with that context, which files or behavior it owns, and how to confirm the result. For example:

Use @agent:<name> as context. Fix the remaining issue it identified in the parser,
add coverage for that case, and report the verification result.

For one particular file or Patch, cite that artifact directly instead of asking the next agent to search the earlier transcript. References are expanded into the prompt when the agent starts, so the next workspace does not depend on files being present in the earlier workspace.

3. Review the follow-up

Watch the new run on the Agents tab. Check that it used the cited result and that its changes answer the next task. Repeat with a new reference if another agent needs to continue the work.

If it goes wrong

If a reference does not resolve, check that its identifier is correct and that the new prompt targets the project that owns the artifact. A local file reference must also be allowed by the project's artifact-reference settings.

_[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.