Skip to content
Monopea

Monopea Teams

People and agents, side by side.

Members, roles and per-project scope, and agent personas with their own brief — the agent can run the workspace admin it is authorised for, and changes to who sees what are proposals.

Start freeSee pricing
workspace · membersAna KellerownerBen RotheditorResearch agentpersonaChloé MartinviewerFinance agentpersona

—

No proprietary file format

9

Agent tools behind this app

1

Approval gate for every outward action

CH · EU

Stored in Switzerland. Processed in the EU.

The Members surface, showing what each role may do — owner, responder and viewer — beside a roster where every person carries the role that decides whether they can approve the agent’s outward actions.
Members · what each role may do, beside the roster it applies to

What you ask → what actually happens

Teams, in the words people type.

Mechanism, not adjectives: each line is what the agent does when you say it.

“Add Marie as an editor on the Q4 project.”

Invites her, with the role and the project scope you named — as a proposal, because it changes who can see your work.

“Give the research agent its own instructions.”

Creates a persona with its own brief and its own visibility, beside the people.

“Who has access to what?”

Reads back members, roles and per-project scope in one answer.

Capabilities

What Teams does.

01

Roles and project scope

Who is a member, what role they hold, and which projects they can see.

02

Personas

Agent personas with their own instructions and visibility, beside the people.

03

Admin by request

The agent reads back and changes membership — as proposals when it changes access.

04

Seats

Each person keeps their own mailbox, calendar and meeting space per workspace.

Tools the agent calls

Real functions, not a chat reply.

Verbatim names from the runtime catalog. Every call is logged; anything outward is a proposal first.

  • manage__get_workspace_overview
  • manage__create_workspace
  • manage__invite_member
  • manage__set_member_role
  • manage__create_persona
  • manage__set_persona_visibility

Governed

It works on its own. It asks at the door.

Inside the workspace the agent just works. Anything above the one risk threshold you set — and anything that leaves — becomes a proposal with its exact arguments, and waits for you.

How the approval gate works
Proposal · send renewal quotedrafted in the workspacecredentials by {{secret}} onlyabove your threshold → askwaiting…Approveactivity logdispatched

Works with

The rest of the suite, one agent.

Agent flows

A canvas for per-project agent teams: who runs, who supervises, and what each one may read. Every sub-agent inherits the same gate, and a stop cascades to everything it delegated.

Explore Agent flows

Channels

Threads, tasks and a living canvas per channel — edited by people and the agent side by side, in the same workspace as the files the work is about.

Explore Channels

Catalog

Connect any MCP-compatible server, or build a tool library from API documentation. New tools start needing approval, and credentials are referenced as {{secret:NAME}} — never shown to the model.

Explore Catalog

FAQ

Teams, answered.

Can the agent add people to my workspace?
It can invite them with the role and scope you name — as a proposal, because it changes who can see your work.
What is a persona?
An agent identity with its own instructions and its own visibility, listed next to the people.
Does the agent need my approval for everything?
No — that would make it a form, not an agent. Work inside the workspace runs on its own; anything above the one risk threshold you set, and anything that leaves the workspace, becomes a proposal with its exact arguments and waits for you.

Hand Teams its first job.

Open a workspace, give the agent a task, and approve what it proposes. Stored in Switzerland, processed in the EU.

Start freeSee every product