Agents with a job to do.
An agent is an AI worker you set up once: what it is for, what it may reach, and when it must ask a person first. Talk to it in chat, give it duties to do on its own, approve what it proposes, and see everything it did.
What makes an agent
- A mandate: instructions in plain words (up to 8,000 characters) and the tools it may use.
- Access: the workspaces and projects it can reach, and what it may read, change or delete there.
- Approvals: when it must ask a person before it acts.
- Sharing: who may use it and who may manage it.
- Duties: work it does on its own. See Duties.
An agent never reaches further than the access you give it, and every change it makes is recorded under its own name.
Create an agent
Open Agents and press New agent
Agents is in the sidebar. With no agents yet, you can start from a template (project manager, documenter, tester or compliance officer) or from scratch.Identity
A name, a character or an icon for its avatar, and a short description.Mandate
Its instructions, and its tools: all of them (new ones included), or only the ones you pick. All tools still never includes billing, members, teams, permissions, brain administration, settings, the organisation itself or other agents. To start quickly, pick a preset: Read only, Editor or Full access sets the tools, when it asks first and the access it starts with. Anything you set yourself stays.Access
Choose which workspaces, projects or folders it reaches, and what it may read, change or delete there. A folder includes every folder inside it. Databases have a row of their own and never follow Documents: with nothing ticked, the agent reaches no database. Access limited to folders reaches none either, because a database is never kept in a folder. Only owners and admins can give an agent the whole organisation.Sharing and approvals
Choose who may use it and who may manage it, and when it asks for approval. Until you share it, only you and your organisation's owners and admins can see it.Review
Read what it will be able to do, then create it. Nothing is created before this step.
When it asks
| Approvals | What the agent does |
|---|---|
| Ask before any change | It reads and answers freely, and proposes every change for a person to approve first. This is where every agent starts. |
| Ask before deleting | It makes ordinary edits on its own, and asks before it deletes or irreversibly changes anything. |
| Don't ask | It acts on its own inside its access. Nobody approves what it does, and every action is still recorded. |
Every level is on every plan. A proposal waits up to 72 hours for a decision. Open Approvals on the Agents page to see what is waiting across all your agents, approve a whole run at once, or decline with a reason that stays on the record. On a keyboard, J and K move between proposals, A approves and D declines.
An agent's page
Each agent has tabs for its Overview, Chat, Duties, Activity and Approvals, then its Mandate, Access and Sharing. The overview shows anything waiting for a person, its approvals and speed, its mandate and access, who owns it, the AI it runs on, and its recent runs.
Chat with it
Message the agent from its Chat tab. Turn on Plan first to see its plan before it starts, and set the approvals for this conversation if you want it stricter than usual. You can also talk to an agent from the top bar, by choosing it in the Ask about menu, or from your own AI tools. A conversation carries on while you work elsewhere, and comes back if you reload the page.
Activity and undo
Activity lists every run, how it started (asked, delegated, from chat, from a duty) and what it did. To reverse a run, choose Undo this job: the agent builds an undo plan, nothing changes yet, and the plan is approved like any other.
Pause, archive and delete
- Pause stops an agent at once, until you resume it.
- Archive puts it away without deleting it. An archived agent does not count towards your plan, and you can restore it from the Archived filter.
- Delete permanently only works on an archived agent, and asks you to type its name.
Owners and admins can also adopt an agent that is waiting for a new owner, and download every agent chat and run in the organisation.
Quick responses or thinking
The Speed card on an agent's overview sets how it works on Stable Baseline's AI:
| Speed | What it does |
|---|---|
| Quick responses | Answers fast. Best for everyday questions and simple tasks. Every new agent starts here. |
| Thinking | Takes longer and works through harder problems step by step. |
A change applies from the agent's next run, and only the people who manage the agent see the card. If your organisation runs everyday or thinking work on its own AI, owners and admins choose each agent's AI under Organisation settings, AI instead. On the Free plan, agents work once your organisation connects its own AI.
What agents cost
Asking an agent costs no credits, within a fair-use number of questions a day for each person, shared with Orbit. Work an agent does on its own, for a duty, uses credits: 1 when it checks and finds nothing to do, 5 when it acts. See what a duty costs. A tool with its own fee costs the same whether a person or an agent uses it.
Limits