Agent Studio

Build agents that work across the platform: the studios are their tools, and they are the studios' tools too. Every agent acts as someone, every tool says what it does to the world, and anything that changes something waits for a person.

The eight studios About Agent Studio

What it is for

It acts as someone: An agent works with the access of the person it works for, or with an account of its own. It can never see more than that.
Tools declare their effect: Each tool is marked: it finds, it proposes, it makes, or it changes. What changes something is held until a person approves.
A member of staff: An agent can have its own account, a supervisor, a duty that can be paused, budgets, routines and a timesheet of the time it worked.
Approvals in the cartable: A held action reaches the supervisor's cartable with what the agent wants to do and why. Approve, decline, or answer.
Reachable from everywhere: In a chat, as a step of a process or a flow, from an app, from the assistant - and from outside through an MCP endpoint.
Runs that survive: A run that waits for a person or a reply is not a held thread: it ends, and takes up again when the answer comes - through restarts too.
One switch: Every agent on staff can be paused at once.

Getting started

Open Agent Studio and describe the agent: what it is for, and for whom.
Check its tools. Each one shows its effect.
Try it in the studio, then publish it and choose where it may be reached.

Tasks

Put an agent on staff

Open the agent and switch Staff on.
Name its supervisor and its budgets.
It gets an account of its own; what it wants to change reaches the supervisor first.

Give an agent a routine

Open the agent's routines.
Say what it should do and when.
It reports to its supervisor after each one.

Use an agent from another tool

Open the agent's channels.
Switch MCP on.
An outside tool that speaks MCP can ask it, within the same rules.

Questions

Can an agent act without anyone knowing?

No. Every run is recorded with its steps, tools and cost, attributed to the agent and to whoever it acted for.

Which models does it use?

The ones you configure: Anthropic's models, any OpenAI-compatible endpoint - one you host included - and the Claude Code, Codex and Gemini command-line engines on your own runner.

Can an agent use a password?

It can use a credential from the Vault for the work it was granted - and never reads its value.

Assistant: One assistant beside every page - that proposes, and obeys.
Cartable: Everything waiting for you, in one list.
Vault: Credentials that are used, never shown.
Orchestration Studio: Connect the systems of the organisation.
Learning Studio: Courses written, examined and tutored by a team of agents.