HomeClaudiaHow it works
How Claudia works

No backend. No account. Your data stays on the phone.

Claudia talks straight from your iPhone to the AI provider you choose, using your own key. This page shows exactly what stays on the device, the one thing that crosses to your provider, and the parts we are honest about not doing.

The boundary

Two places exist. Almost everything lives in one.

There is your phone, and there is the AI provider you picked. Nearly everything Claudia touches stays on the phone. Exactly one thing crosses over, and only when you send a message.

📱 On your phone
  • Your chats and history
  • Everything Claudia remembers
  • Your API keys iOS Keychain
  • Your settings and personalization
Never uploaded
Your phone’s edge
What crosses
Your message, with names, emails, and numbers masked first.
Only this. Nothing else.
The provider you chose

Anthropic, OpenAI, Gemini, or another. It receives the masked request, authenticated with your key, and sends an answer back. The same as using their own app with your own key. We are not in the path.

Follow one message

The whole journey of a single request.

Say you tell Claudia text Cass at 2pm. Here is everything that happens to it.

01

You type it

The words sit in the on-device database on your iPhone. Nothing has left yet.

02

It is masked on the device

Before anything is sent, Claudia swaps out names, emails, and phone numbers for placeholders. Cass never leaves the phone as a name.

leaves as → text {{PERSON_0}} at 2pm
03

It goes straight to your provider

The masked request travels from your phone to the provider you chose, signed with your key from the Keychain. There is no PrentusAI server in between, because there is no PrentusAI server at all.

04

The reply is restored on the device

The answer comes back and the placeholder turns into Cass again, on your phone. You read a normal message. The provider only ever saw a token.

{{PERSON_0}} becomes → Cass
What this does not do

The parts we would rather tell you.

Privacy claims are easy to make and easy to overstate. Here is where the line actually is.

Inference is not local

The model runs on your chosen provider's servers, not on your phone. If you need fully offline, on-device inference, Claudia is not that. What stays local is your data, your memory, and your keys.

Free-typed details are not masked

The masking covers names, emails, and phone numbers. If you type a street address or an account number straight into the chat, it reaches your provider as written. Treat the chat the way you would treat their own app.

It is closed source today

You cannot read the code yet, which is exactly why this page spells out what happens. We are open to an outside review of the data handling.

By construction

The shape of it, in plain terms.

What we never get

There is nothing for us to hold.

  • × No PrentusAI account or login
  • × No PrentusAI server in the request path
  • × No analytics, tracking, or ad SDKs in the app
Two more things

Actions wait. Keys are yours.

Calendar events, messages, and reminders show you a card and do nothing until you tap to confirm. Text that Claudia reads from a web page cannot act on its own.

And Claudia is free. You pay your provider directly for what you use. We do not resell tokens or take a cut.

Private by construction

Not a promise about your data. The absence of a place to keep it.