Scenario

Scenario · owned by Admin

Drafts a fourth path from a conversation — forks a scenario and changes only the fields you named, with a required rationale. It never applies anything: a drafted scenario is a preview that waits for your explicit approval before it’s saved.

Active

Autonomy

The trust dial: how freely the agent acts on things it's already allowed to do. Even at full autonomy, it can never reach beyond its permissions.

Acts, but every action needs approval

Scope

What the agent may touch. Anything not explicitly allowed here is off-limits by default — no exceptions.

	Read	Sync	Flush	Restart	Roll back	Rotate	Invoke	Draft	Notify	Move to Trash	Submit	Send	Configure	Purchase
Service
Integration
Deployment
Data store

Default deny — access exists only where explicitly granted.

Guardrails

Safety rules on top of permissions — the strictest rule wins. A guardrail can send even a fully-autonomous agent to a human for approval.

Production needs approval

Any action on a production target drops to the approval queue.

Rollback needs approval

Rollbacks always require a human sign-off.

Blast-radius cap

Limit how many resources one action may touch.

Rate limit

Cap actions per rolling hour.

Max actions / hour

Ask when unsure

The agent acts on its rules alone, but anything it can’t confidently decide comes to you for approval.

Binding actions need approval

Anything that commits you — submitting, sending, changing a setting — waits for your yes.

Ownership

Every agent answers to a responsible human. If that person leaves, the agent pauses itself — nothing keeps running with nobody accountable.

Owner: Admin

Activity

What this agent has attempted, each decided live by the engine. Run its next scripted action, or type one in plain language.

Run this agent’s actions

Next · step 1 of 2

invoke draft-scenario · staging

Draft a fourth path from the conversation — fork a scenario, change only the fields you named.

Try:

No attempts yet — run an action and watch Warden decide.