How it works

How Sona builds your twin

No magic, no hype. Five layers around one core, and you see and control every step.

One core, five layers

At the center is the Persona Core, the model of who you are. Five layers sit around it: one learns you, one makes you sound like you, one gives you ways to reach your twin, one lets it act, and one keeps everything safe and yours. Click through them.

  • YouOne core, five layers around it.

Layer 1 of 5

Capture: how Sona learns you

Your twin interviews you. Relaxed conversations, by voice or text, that follow whatever you talk about most easily. Life Import connects the chats, mail, notes, and calendar you choose to share. And it keeps learning: about ten minutes of conversation a day, which becomes a habit rather than a form to fill in.

Persona Genesis runs an adaptive interview of 40 to 60 questions, and the questioning strategy shifts toward whatever you have most to say about. You can watch your persona completeness update in real time. Life Import starts learning your style from as few as 20 messages, sharpens through the first hundred, and keeps refining across several hundred more, all strictly by explicit consent. A 1 to 5 minute voice sample builds your Voice Twin.

It feels like talking to a curious friend. Underneath, it is building a structured picture of who you are.

The recognition test

Every layer gets tested the same way

One question decides it: can someone close to you, in a blind chat, tell your twin apart from you? When the answer is no, we have done our job. It is an ambitious bar, and it is measurable: blind A/B conversations, automatic style scoring, likeness as a number we can show you.

Should I take the job in another city, or stay close to family?

Same question, sent to two chats. One is a person. One is their Sona twin.

Chat A

Honestly? Run the version where you stay and the version where you go, then check which one you keep talking yourself out of. That's usually the one you actually want.

Chat B

Don't decide it as a job - decide it as a year of your life. What do you lose if you stay, and is that a story you'll be at peace telling later?

Illustration of the recognition test.

How it works FAQ

How long does it take to build a good twin?
A useful text twin starts working in your first few sessions. It keeps getting closer the more you talk to it, and it keeps learning as you change.
How much of my data does it need?
Less than you would think. Around 20 samples of your writing is enough for your style to start landing, and it keeps getting closer with every conversation. The interview does much of the work, and you add only what you choose to add.
Will it pretend to know things it does not?
It is built not to. Truth Anchor keeps your twin to facts from your own material, and when something is missing it says "let me check with the real me" instead of guessing. Generative models can still get things wrong, so review anything that matters.
Can I control what it is allowed to do?
Yes. That is the Values Firewall: you set the topics it will not touch and the actions it cannot take, it asks before acting, and every action is logged.

Become the second version of yourself

Join the waitlist and be among the first to build your twin. You will own it, and one tap deletes it.