Skip to content

Work units

SASE uses separate records for the outcome a person wants, the work planned to reach it, and the changes that need review.

The idea in one picture

Goal ──► Plan ──► Beads ──► Agent work ──► Patch
 desired    approach  work items              review
 outcome

This is one way to connect the records on a larger piece of work; a small change may use only some of them.

How it works

A Goal describes a result a person wants and how they will recognize it. A plan records an approach; a larger plan can be broken into phases and dependencies. Beads track the individual work units that agents or people can pick up. A Patch gathers a proposed code change with its review state.

These records answer different questions. A Goal says what should become true. A plan explains an approach. A bead identifies work to do. A Patch makes a resulting change reviewable. Keeping those roles distinct makes it possible to revise a plan, retry one work unit, or review a change without losing the desired outcome.

When it matters

  • Start with a Goal when the desired result needs a durable owner or progress history.
  • Use a plan and beads when work needs decomposition, ordering, or explicit handoffs.
  • Use a Patch when a change needs review and a record of its lifecycle.

Do it

Look it up

_[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.