Private AI for Solicitors: A Private LLM in Your Own Office
Fee earners with a bundle to read by Thursday are pasting correspondence into whatever chatbot is open. A private LLM for law firms gives them the same tool on a machine the firm owns, with privilege intact.
£500 per month for the software and the hardware rental. You rent the machine — you don’t buy it.
Private AI for solicitors is a private LLM running on a dedicated machine in the firm, so matter files, correspondence and precedents can be searched, summarised and drafted against without privileged or confidential material reaching a third-party provider. It never gives legal advice, and it is installed and supported by us.
See what a private assistant would read
A short call with a partner or the COLP. Bring your engagement terms and your insurer’s AI questions; we will walk through them.
A private LLM with chat, document spaces and assistants on one machine in the firm. Matter files never leave the office.
Cloud Agents for Intake, Local AI for the Matter Files
New-client calls and the general enquiries inbox carry little that is privileged, so firms run those on our hosted agents and keep client files on a Local AI machine in the office.
- ☁ Cloud-based AI Receptionist
- ☁ Cloud-based Email Manager
- ☁ Cloud-based Leads Outreach
- 🏢 On-premise Local AI
The Ban Does Not Work. The Alternative Does.
Staff at law firms who need a letter drafted quickly are already using a chatbot. A blanket ban moves that out of sight; it does not stop it.
| Public chatbot | Private AI in the firm (ours) | Private LLM you build yourself | |
|---|---|---|---|
| Where prompts and files go | The provider’s servers | A machine in the firm | A machine in the firm |
| Chat history stored | With the provider | On your machine | On your machine |
| Used to train models | Depends on the plan and settings | Never | Never |
| Who can see who used it | Nobody in your business | You, through your own sign-in | You, if you build the access control |
| Reads your document library | Only what someone pastes in | Yes — spaces with citations | If you build it |
| Installation and upkeep | None | Us | Your IT person, indefinitely |
Privilege Does Not Survive a Paste
Three pressures land on a law firm at once. The SRA expects client affairs kept confidential. The Law Society’s guidance on generative AI expects the firm to know where client data is processed. And professional indemnity insurers have started asking, at renewal, how the firm uses AI. Against all three stands a fee earner with a bundle, a deadline and a public chatbot — and privileged material that has just been disclosed to a provider whose terms nobody at the firm has read.
A private LLM for law firms is the answer that lets the firm say yes instead of no. The model runs on a machine in the office. Matter files, correspondence, counsel’s advice and precedents go into document spaces organised by matter or practice area, and every question is answered in the room. Privileged material is not disclosed because it is not sent anywhere. Which fee earners see which matters follows the Microsoft 365 or Google Workspace sign-in the firm already administers.
What fee earners do with it is what they were trying to do in the chatbot, done properly: a chronology from three years of correspondence with every entry cited to the page; the clause in a lease; the differences between two versions of an agreement; a first draft from the firm’s own precedent in the firm’s house style, handed to a supervisor. Not advice. Every output is a starting point for a qualified person, and the training says so.
The case management system is not connected and remains the system of record. We install the machine, import the first practice area’s files and train the fee earners, then handle updates, model upgrades and support under a data processing agreement drawn narrowly enough for a partner to read in one sitting. The insurer’s question gets a one-sentence answer.
One thing fee earners notice within a week is the citation. A public chatbot summarises correspondence confidently and invisibly; the private assistant’s document spaces return the passage and the page it came from, so a trainee can check the source before a supervisor sees the draft. For a firm, that is not a convenience feature. It is the difference between an assistant that can be used on a matter and one that cannot.
One Private AI Machine, Three Tools On It
Everything runs on the one machine in the firm, and your team log in with the accounts they already have.
A private AI chatbot for the whole team
A ChatGPT-style assistant on your own machine. Staff ask questions, upload documents and images and work through drafts, and none of it leaves the building.
Document spaces
Files and correspondence organised into spaces. Search, summarise and compare across hundreds of documents, with a citation to the page every answer came from.
Custom assistants
The monthly report, the standard memo, the routine check — built around your workflows and running on the same machine, covered by the support arrangement.
| Document | What the fee earner asks for | What stays where |
|---|---|---|
| Correspondence on a matter | A chronology, every entry cited | On the machine, in the office |
| Bundles and disclosure | A summary; the passages on a point | On the machine, in the office |
| Leases, contracts, agreements | What clause 14 says; the differences between two versions | On the machine, in the office |
| Precedents and house style | A first draft, for a supervisor to review | On the machine, in the office |
| Counsel’s advice and privileged notes | Searchable within the matter, by permitted staff | On the machine, in the office |
| Case management system | Not connected — remains the system of record | Your existing system |
From a Partner’s Call to a Private LLM in the Firm
Weeks, not months. Most firms start with one practice area and widen once it is in daily use.
A call with a partner or the COLP
Practice areas, headcount, which team goes first. We specify the machine from that and walk through the data flow.
Install and import
The machine goes on the firm’s network. Sign-in connects to your Microsoft 365 or Google Workspace. Files, correspondence and precedents for the first team are imported into spaces.
Train fee earners, then support
We train the people who will use it, including what it is not for. Updates, model upgrades and support follow, from the people who installed it.
Where Local AI Is the Wrong Answer
We would rather lose the enquiry than the trust. Three things we tell every prospect before they sign anything.
It will not make you compliant by itself
No product can make a business UK GDPR-compliant on its own. What private AI does is remove the hardest question from the assessment — where the personal data goes. Lawful basis, retention and staff conduct remain yours.
It is slower than the big cloud models
Open-weight models on a single machine are capable for summarising, drafting and answering questions about your own documents. For frontier reasoning on hard, novel problems, the largest cloud models are still ahead. That is the trade.
It is a weeks-long install, not a sign-up
A cloud agent is live in days. Local AI needs the machine specified, delivered, installed on your network and your documents imported. Weeks, not months — but not tomorrow.
Private by Construction, Not by Policy
Nothing leaves the building
Open-weight models, documents and chat history all live on the box. No third-party AI processor and no restricted transfer for the AI step.
Your sign-in, your access list
Single sign-on with Microsoft 365 or Google Workspace. You decide who has access with the tools you already administer.
Never trained on your content
Your documents and conversations are not used to train or improve any model. The models arrive trained and stay that way unless you ask.
Installed and supported by us
Hardware, installation, training, updates and support from one team, with a data processing agreement covering the support access you grant us.
Which Page Answers Your Firm’s Question
| If your question is… | The short answer | Read more |
|---|---|---|
| What is the full private AI setup? | One machine: chat, spaces, assistants, support | Private AI |
| We want the Local AI overview for solicitors | The head page for law firms | Local AI for solicitors |
| What does the COLP need to see? | No processor, no transfer, for the AI step | GDPR Compliant AI for solicitors |
| Which model would run on it? | An open-weight local LLM, matched to the work | Local LLM for solicitors |
| We would rather host it ourselves | It sits in your building; we maintain it | Self-Hosted AI for solicitors |
| We are a City firm | Private AI installed across the capital | Private AI London |
| Why on-premises at all? | The case for Local AI, in full | Local AI product page |
Private AI for Law Firms: Common Questions
What is private AI?
AI that processes your prompts and documents on hardware you control instead of on a provider’s servers. With ours, the model, the chat history and every uploaded file stay on a machine in the firm. Nothing is sent to an outside service to produce an answer.
Is a private LLM as good as ChatGPT?
For everyday work — summarising, drafting, extracting, answering questions about your own documents — it is capable and most offices are happy with it. It is somewhat slower, and the largest cloud models are still ahead on hard, novel reasoning. That is the trade for keeping data in-house.
Is a private LLM consistent with our SRA confidentiality duty?
That is the firm’s judgement, but the facts are simple: the model, the documents and the chat history stay on a machine in your building. There is no third-party AI processor and no transfer. Bring your COLP to the call; these are the questions we would rather answer early.
What do we tell our professional indemnity insurer?
That AI use at the firm runs on a machine in the office, that no client material is sent to an AI provider, that outputs are drafts reviewed by a qualified person, and that access follows the firm’s existing controls. We will put it in writing for the renewal form.
Can a fee earner check where an answer came from?
Yes, and for legal work it must be possible. Document spaces return answers with a citation to the page they came from, so the source can be checked before anything is relied on. A public chatbot summarising pasted correspondence gives no such trail.
Does it give legal advice?
No. It drafts, summarises and finds. Every output is a starting point for a fee earner, and anything constituting legal advice stays with a qualified person. We say so in the training and we would say so to your insurer.
Can it read our case management system?
It does not connect to it. Documents and correspondence are exported into spaces on the machine, organised by matter or practice area. The case management system stays the system of record.
How much does Local AI cost?
£500 per month for the software and the hardware rental. The dedicated machine is rented to your business, not sold: you never buy the hardware. It is installed in your building and runs the private chat, document spaces and assistants. Local AI is for business customers only.
Give Fee Earners the Private Version
Tell us your practice areas and what fee earners are pasting into chatbots today. One short call to size the machine, with your COLP welcome on the line.
Prefer email? sghaith@businessaiagents.co.uk