Every solicitor evaluating an AI tool asks the same question, usually a little too late: when I put this matter into the box, where does it actually go?

It is the right question. Most tools answer it badly, or not at all.

Two architectures, one that matters

Broadly, an AI product for a law firm is built one of two ways.

In the first, the document leaves your machine. It is uploaded to the vendor's servers, processed there, and stored there — often to "improve the service". Your control ends the moment you click send.

In the second, the document never leaves your machine at all. The matter lives in your browser, on your own disk. When you ask the AI to draft or analyse, only the specific text you approve for that one step is sent — nothing else, and nothing in the background.

The difference is not a feature. It is the whole question of whether you can put a privileged file into the thing.

Where the privilege line actually sits

Legal professional privilege in England and Wales is a duty you cannot casually delegate to a supplier — and in some jurisdictions the professional-secrecy duty is stricter still, closer to an absolute prohibition than a best-efforts promise. "We take security seriously" is not a lawful basis for putting a privileged communication onto a third party's servers.

So the test is simple, and it is architectural, not contractual: does the privileged material have to leave your machine for the tool to work? If the answer is yes, no amount of encryption changes what you have done — you have disclosed it to a processor.

What "browser-resident" means in practice

A browser-resident tool keeps matter data in your browser's own local storage. There is no vendor database of your files to breach, subpoena, or forget to delete. Before anything reaches an AI model, a check runs in your browser — a privilege gate. It warns you before privileged content would leave, and where the professional-secrecy duty is absolute it can hard-block outright. You decide, every time, with the line drawn before the send, not after.

The key question behind the key

There is a second question hiding inside the first: whose AI key is it?

On a managed key, the vendor mediates every call — convenient, but it means the vendor sits in the path. Bring-your-own-key (BYOK) puts your own provider credentials in play, so your usage is billed to you directly, at your provider's rates, and the path is yours. For a firm that wants the shortest possible line between its desk and the model, that shortness is the point.

A short checklist for any AI tool

Before you put a real matter into anything, ask:

  • Where is matter data stored at rest — my machine, or your servers?
  • What exactly leaves my machine on each AI call, and can I see it first?
  • Can privileged documents be hard-blocked from leaving, not merely flagged?
  • Who can read the logs, and can I export a record of what the AI did?

The blunt version: if a tool cannot tell you precisely what leaves your machine and when, assume everything does — and treat it accordingly.

That is the standard we built to, because it is the only one a careful firm can actually defend.

← All posts