Briar

How Briar works

The question nobody in this category answers.

An insurance document contains a name, a date of birth, financial figures and often a medical history. Several major AI providers explicitly forbid being sent exactly that. Here is what Briar does instead.

Updated 6 min read

The short answer

Briar reads client documents on the machine it runs on, using a local model, with no fallback that sends them elsewhere if that model is unavailable. The overnight pass that reads client files for opportunities works the same way. Dates of birth, premiums, coverage amounts and medical detail stay on your own hardware.

Why this is a real question and not a compliance formality

A single life insurance document routinely contains a full legal name, a date of birth, a policy number, a face amount, a premium, a bank account for the draft, and — on an application or an underwriting letter — a medical history. That combination is close to the definition of sensitive personal data.

The part most buyers have not checked is that several major model providers do not merely warn about this. Their acceptable-use terms prohibit sending financial or medical information and dates of birth to the service at all. That is a prohibition rather than a permission you can apply for, and it is not fixed by an enterprise plan or a checkbox.

What Briar does

  1. 01

    Documents are read on your machine

    The model that reads a carrier PDF, a scan or a photograph runs on the hardware Briar is installed on. The page never leaves it.

  2. 02

    There is no hosted fallback on that path

    This is a deliberate design decision and the more important half. A fallback fires when the local model is busy or down — at three in the morning, unwatched — and it would send exactly the data the rule exists to protect. A degradation that breaks the rule is not a degradation, it is the incident.

  3. 03

    The overnight analysis is local too

    The pass that reads client files looking for opportunities is the one that assembles the most sensitive payload of all: name, date of birth, policy values, and a prompt asking the model to look for serious illness. It runs on the same local model, on the same machine, with the same absence of a fallback.

  4. 04

    The two are switched separately

    Reading documents and analysing the book are different lanes with different switches, because a refused document read and a refused analysis fail in completely different ways, and one flag for both would hide the second.

What does still leave, stated plainly

It would be easy to write "fully local" here and it would not be true. Briar routes each job to the model measured best for it, and two categories still use hosted models:

That is the honest boundary as it stands today, and it is the boundary a buyer should ask every vendor in this category to draw. A vendor who cannot draw it has not thought about it.

The other half: isolation between agents

Separation between one agent's book and another's is enforced by the database rather than by application code. Every tenant table carries a policy PostgreSQL applies to every query — 52 tables as of this writing, verified automatically — so a bug in the application cannot leak across agents, because the application is not what is enforcing it.

Documents are stored once, by hash, encrypted at rest. Every automated decision Briar makes on its own judgement is logged with the evidence behind it, so "why did that end up there" is always answerable.

Questions

Asked and answered.

Does Briar send my client documents to an outside AI company?
No. Carrier documents, scans and photographed pages are read by a local model on the machine Briar runs on, and there is no fallback that sends them out if that model is unavailable. The overnight pass that reads client files for opportunities runs locally on the same basis.
Is it against AI providers' terms to send them insurance documents?
Frequently, yes. Several major providers' acceptable-use terms prohibit transmitting financial or medical information and dates of birth to the service. Because those are exactly the fields a policy document exists to convey, redacting them before sending is not a workable answer.
How is one agent's client data kept separate from another's?
By PostgreSQL row-level security rather than by application code. Every tenant table carries a policy the database applies to every query, across 52 tables, so an application bug cannot leak across agents. Coverage is verified automatically rather than by review.
Can Briar work without an internet connection?
Not entirely. Document reading and the overnight analysis run locally, but the mailbox, the conversational assistant and letter drafting need a connection. The local half is about where sensitive documents go, not about running offline.

Early access

Briar does the admin. You do the part only a licensed human can.

Briar is onboarding a small number of independent life agents. If you are spending your week on administration instead of clients, get in touch and tell us what your week actually looks like.