Your material sits in your own encrypted space in our private cloud on Amazon Web Services, scoped to you and nobody else — never pooled, never shared, never used to train anyone else's model. The controls below are not switches buried in a settings screen; they are commitments, held in writing. Here is each one, plainly.
Where your material lives
In your own encrypted space: your files, your messages, the assistant's memory of them — encrypted at rest with keys held in AWS KMS, and encrypted whenever it moves. The stores that hold it have no public endpoints; there is no address on the open internet where your archive can be asked for. The less your information travels, the less can happen to it — and inside our boundary it travels very little. The fuller story is at where it runs.
Which models do the thinking?
The strongest commercial models are part of the service — chosen by us for each kind of work, and paid for out of the same fee. Your assistant reaches them through Amazon Bedrock, inside the same boundary as everything else, and that traffic travels AWS private networking, not the public internet. In the hardware era you held a valve that decided when an outside model was used; that valve is gone, because the boundary it guarded is gone — the models sit inside the service now, and there is no extra bill for using them.
What do the models see?
Only what a given piece of work needs — the minimum context retrieved for that question. Guardrails run on model traffic in addition to our own authorization rules, and what the models see is not used to train them and not shared with the companies that make them.
What happens only with your yes
Anything consequential — sending and booking — happens only with your approval. Approvals expire rather than lingering, and everything is logged, so what your assistant did and why is a record you can read, not a claim you have to trust. Answers cite your own records — source, date and location kept end to end — so you can check them before you rely on them.
What you can connect
Today: Gmail, Google Calendar, Google Drive and Google Contacts; Microsoft 365 — Outlook, Calendar, OneDrive and SharePoint; files, from Dropbox, Drive, OneDrive or sent directly; Telegram; and email. Next, with no dates promised: HubSpot, QuickBooks, DocuSign and Adobe Sign, and Slack. Connecting something new, or widening what your assistant may reach, happens only with your yes — it widens what it can see, so it is yours to allow. The credentials that make each connection are held server-side in a secrets vault, retrieved just in time, and never shown to the models.
What you can ask us to do
Ask us to correct or delete something the assistant remembers and it is honored, confirmed in writing. Ask for a complete copy of your material at any time and you receive it. And when the service ends, your space and everything in it is deleted — confirmed to you in writing, like everything else between us.
Are security and support included?
Yes: updates, security fixes, health checks, backups and human support in writing are all inside the service. Write to support@digitaltwinpro.com and we reply in writing within one business day.
Last updated: September 2026.
Your own AI. Your own material. One assistant, yours alone.
$9,995 the first year — everything included. $5,995 each year after. The first year costs more because it contains the preparation — your archive prepared and loaded by hand under a written scope, and your assistant built on it — as well as the first year of the service; every year after is the service running.
Or add the Archive Assessment first — $1,950, credited in full
You order and pay at checkout; we write back within days — a decline returns every dollar, and until our letter confirms the year you may withdraw in writing. From that letter the year is final, and it arrives on the date the letter names. Prefer to write to us first?