Make and review a change¶
This tutorial asks an agent to make one small edit in the demo workspace and shows you how to review it.
Before you start¶
You need to have completed Run your first agent and have an authenticated provider available.
1. Ask for one small edit¶
Before starting the run, know what happens when the agent submits its final declaration:
SASE's default host finalizer commits the change and pushes it to the +home project's
remote. That remote is a local bare repository, so this does not publish your change to
a public hosting service.
Ask the agent to create one file with one line:
sase run "+home create welcome.txt containing exactly this line: My first SASE change. Do not edit other files."
The agent works in an isolated workspace. Its prompt asks for one file, but workspace isolation does not enforce those instructions. Review the result before using the same workflow with one of your own projects.
2. Inspect the change¶
Open the terminal interface:
sase tui
On the Agents tab, find the run that created welcome.txt and wait for it to finish.
Open the Commits pane in Artifacts, select the new commit, and press Enter to read its
message and diff.
You have made and reviewed a change¶
You have seen the file change and the commit that records it in SASE's demo project.
Next¶
_[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.