Agents, sessions, and workspaces

Agents do delegated work in project workspaces, while sessions keep related turns together when work needs to continue.

The idea in one picture

Prompt or macro ──► Agent ── works in ──► Workspace
                       │
                       └── results and progress ──► TUI

How it works

A stand-alone agent performs one turn; a session groups related turns into a sequential chain, so later work can continue from earlier work rather than starting as an unrelated task.

A workspace is an isolated checkout of a project. SASE assigns each running agent its own workspace, which lets agents work in parallel without sharing the same working files. Their prompts, output, status, and produced files remain available after a turn ends.

The TUI presents active and completed agents alongside their work records. It gives a person a place to follow progress, inspect results, and decide what should happen next.

When it matters

• Use separate workspaces when agents need to change the same project at the same time.
• Use a session when related turns need to build on one another.
• Return to the TUI when you need to find an agent's progress or review what it produced.

Do it

• Run agents in parallel — split independent tasks across isolated workspaces.
• Hand a result to another agent — give a follow-up run the context it needs.
• Get started with SASE — run and inspect a first agent task.
• Recover an interrupted agent — restart, resume, or revive a broken run.
• Unstick a queued agent — clear capacity waits and holds.

Look it up

• Agent sessions — session and grouping details.
• Workspaces — workspace behavior and provider ownership.

_[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.