Mid-size · IT-owned deployment

The answer to the client security questionnaire.

Mid-size firms are large enough to be asked hard questions about data handling and small enough that a negative answer costs a panel place.

Request a Briefing See what it does

What a mid-size deployment looks like

Workstations per practice group, administered by your own IT.

Deploy where the volume is

A workstation per practice group rather than a firm-wide platform rollout. Litigation and transactional can start independently.

Your IT keeps control

Your patching, your backup policy, your access control. No vendor console holds a key to your matters.

Client questionnaires answered

Where is data processed, who sub-processes it, what is retained — all answerable in one sentence.

Matter-level restrictions enforced

A client who forbids automated processing can be recorded as such, and the restriction enforced rather than remembered.

What stays true on every matter

These do not change by practice area, firm size, or the question asked.

Nothing leaves the firmNo cloud, no API call, no telemetry. The matter is read on hardware the firm owns.

Owned, not subscribedA one-time purchase. No per-seat monthly fee and no usage meter.

Citations verified on-machineAuthority is checked against a local corpus, not recalled from a model’s memory.

The entire matterFull workup across the whole file — not a chat window over one document.

Runs on your workstationA current RTX-class GPU. Designed to run with no internet connection at all.

Bring IT and the risk partner.

Mid-size deployments succeed or fail on the IT and risk conversation. We would rather have it at the start.

Request a Briefing

Questions firms ask

The answers below are specific to this page’s subject.

How do we roll this out across practice groups?

Per workstation, wherever the document volume is. There is no firm-wide platform migration to schedule.

Can we pilot it in one group?

Yes, and we would recommend it. Define what an acceptable result looks like before the pilot rather than after.

How does it fit our existing stack?

It reads from the firm's own storage and writes work product back. Deliberately few integration points, because each one is another path data could take.

What do we tell clients who ask about AI?

That analysis runs on firm-owned hardware and their file does not leave it. That answer survives follow-up questions.

Other pages covering the same ground from a different angle.

Enterprise / large firm offline legal AI Private AI for small law firms On-premise legal AI platform Air-gapped AI for law firm data security On-premise vs cloud legal AI In-house legal team private AI

See it run on a real matter.

A briefing walks the whole path — intake, workup, the Adjudicator's pass, and the work product that comes out the other side.