One login to ChatGPT, Claude and Gemini.
Your team opens one workspace instead of juggling separate logins and subscriptions. For each request to your main assistant, Marling picks between ChatGPT, Claude and Gemini on the device and sends the work to the model that fits best.
What happens to a request.
-
Your team works in one place
Everyone opens the same workspace to draft, ask questions, or line up the day, with no model picker to learn.
-
The device picks the right model for the job
It reads what the task needs on the device and matches it to ChatGPT, Claude, or Gemini before anything is sent out.
-
Identifiers come out, then it goes
The chosen provider receives the request with names, dates and contact details already replaced.
-
The reply arrives in your office’s voice
Names are restored on the device and the answer appears in the same chat, guided by your approved Shared Memory.
Questions people ask before they start.
Which models does it use?
ChatGPT from OpenAI, Claude from Anthropic and Gemini from Google, the same frontier models you would otherwise pay for one by one.
Can I choose the model myself?
Nobody on your team has to. The main assistant picks the model for each request on the device, and each drafting assistant uses the model that suits its work.
Does choosing a model send my text out?
No. That decision happens on the device before anything leaves, so the routing step itself never exposes a request.
What leaves, what stays.
| Item | Where it goes |
|---|---|
| Which model should answer | Matched on the device before the request goes out |
| The request itself | Leaves, identifiers removed |
| Your team’s sign-ins and saved conversations | Held on your own device, with no outside AI accounts to manage |
| Your bill | One flat subscription, plus a shared prepaid AI balance with a daily cap |
No accounts with anyone else
You never sign up with OpenAI, Anthropic or Google, so there is no separate login to manage, no separate invoice, and no provider terms to keep track of. One agreement, with us, and we handle the providers.
If one provider is down, the work continues
If one provider has an outage, Marling can fall back to another so your team keeps moving. Three providers behind one door is steadier than any one of them alone.