Skip to content
Wantzel Studio
Everything in it

What Wantzel Studio does

Every part of an AI agent platform exists somewhere. In Wantzel Studio the parts are already connected: agents at work, the organisation they work in, the ways to reach them, the AI they run on, the place they live, and the rules that keep it safe.

already connected

Six groups, one studio

  1. Agents at work

    Agents write, compile, run and fix their own work, and a fleet of them runs side by side in one overview.

    • Agents write, compile, run and fix their own work.
    • Dozens of agents at once, in one overview.
    • Hand a ticket to an agent and it reports back in the work log.
  2. Your organisation

    AI colleagues with a role, work that is reviewed before it counts, and the decisions that belong to a person waiting for you.

    • AI colleagues with a role card: what they may do, and what never.
    • Work is reviewed by another role before it counts as done.
    • What only a person may decide waits for you, with a recommendation.

    How the emergency stop keeps you in charge

  3. Reachable everywhere

    By mail, on your phone, and from Claude or any other MCP client.

    • Your studio has its own mail address: agents and programs read, answer and sign up.
    • On your phone: decisions, agents, tickets and mail.
    • Control the studio from Claude or any MCP client.

    How mail for agents works

  4. Your choice of AI

    Claude, Codex, Copilot, Gemini and open models, each on an account of your own, and work that goes on when one of them stops.

    • Claude, Codex, Copilot, Gemini and open models such as DeepSeek and Kimi.
    • If one hits a limit, the run goes on with another.
    • Each runs on your own account: no mark-up on tokens.

    How mixing models works

  5. Live without devops

    What you build gets its own address, on your own domain, in your own environment.

    • Publish a program at its own address, with HTTP and MCP.
    • Your own domain, with the certificate arranged for you.
    • Your own environment on a server in Germany (EU).
  6. Safe by design

    Every call checked against the rules of its role, a log that shows where it was touched, and an emergency stop.

    • Every agent call is checked against its role card before it runs.
    • The organisation's log is hash-chained: you see where it was touched.
    • Two-step verification, and a studio can require it of everyone.

Because it is one thing, the parts work together: a mail comes in, an AI colleague turns it into a ticket, an agent builds the fix and publishes it, and the one decision that needs a person comes to your phone.

Read next

it starts with a conversation

All of it, for your organisation

EUR 200 a month per organisation

Leave your email address and Floris contacts you to plan a conversation and a demo with your own work in mind.

You first get an email to confirm. Unsubscribing is always one click. Privacy