Automation and human checkpoints¶

SASE moves repeatable work forward in the background and brings people in when a decision needs review.

The idea in one picture¶

Scheduler ──► recurring work and reviews ──► decision
                                              ├── autonomy profile ──► automatic outcome
                                              └── gate ───────────────► human checkpoint

The diagram shows how background work can proceed under an autonomy profile or pause for a person's decision.

How it works¶

The scheduler runs recurring routines. Mentors can review proposed changes and leave findings for a person to consider. Plan approvals put a checkpoint on a proposed approach, so it can be accepted or sent back with feedback before work proceeds. Other gates present their available choices and keep the decision attached to the work.

Autonomy profiles set how supported approval gates are handled. A profile can allow a decision to proceed automatically or leave it for a person. Checkpoints make the choice visible and preserve human judgment when the work needs it.

When it matters¶

Automate recurring checks when the same work needs to happen over time.
Use mentor reviews to surface focused feedback on proposed changes.
Keep a person in the loop when a choice depends on context or carries a meaningful tradeoff.

Do it¶

Get started with SASE — run an agent and review its result.
Schedule recurring work — run a check on a schedule.
Get automated code review — review each change automatically.

Look it up¶

Scheduler — recurring routines and jobs.
Mentors — automated review of proposed changes.
Notifications and gates — approval requests and decisions.
Autonomy profiles — supported automatic gate decisions.
Glossary — scheduler and gate terms.
Design decisions — how gates keep decisions reviewable.

_[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.