Local LLM for Dental Practices: A Model in the Practice, Managed
A practice does not need to know what a language model is to benefit from one. It needs the letters drafted, the policies findable and the patient information kept in the building. The model is our problem.
£500 per month for the software and the hardware rental. You rent the machine — you don’t buy it.
A local LLM for dental practices is a language model running on a machine inside the practice rather than a provider’s cloud, chosen for the practice’s letters, referrals, policies and complaints. It reads administrative documents only, stays out of the clinical system, and is installed, kept current and supported by us.
Find out which model suits the job
A short call with the practice manager or principal. If your paperwork does not justify a machine, we will say so.
One machine in the practice office, an open-weight model chosen for practice paperwork, and the chat and document tools around it.
Cloud Agents for the Front Desk, Local AI for the Records
The phone and the enquiry inbox are not where a practice’s confidentiality problem lives, so most practices run those on our hosted agents and keep patient documents on the Local AI machine.
- ☁ Cloud-based AI Receptionist
- ☁ Cloud-based Email Manager
- ☁ Cloud-based Leads Outreach
- 🏢 On-premise Local AI
Do It Yourself, or Have It Done
Running a local LLM is not hard for an afternoon. Running one for dental practices, every working day, with backups and someone to ring, is a different job.
| DIY on a spare machine | Cloud LLM subscription | Managed local LLM in the practice (ours) | |
|---|---|---|---|
| Where prompts and files go | Your machine | The provider’s servers | Your machine |
| Choosing local LLM models | Trial and error, evenings | No choice | Tested against your documents by us |
| Hardware | Whatever is spare | None | Specified for the team and rented to you |
| Reads your document library | If you build it | Only what is pasted in | Document spaces with citations |
| Model upgrades and updates | You, when you remember | Automatic | Us, as part of support |
| When it breaks | You | Their status page | Restored from backup by us |
Chosen for Letters and Policies, Not for Benchmarks
Nobody in a dental practice wants to choose a language model, and nobody should have to. What a practice wants is narrower and clearer: referral letters drafted well and in the practice’s own wording, complaint responses that are careful and complete, policies and SOPs findable with their review dates before a CQC inspection, and patient information that never leaves the building while any of that happens. Those requirements pick the model.
They point at open-weight models that write good, plain English and are reliable at finding the right passage in a folder of policies — not at the largest or newest model on a leaderboard. The document set in a practice is modest, so the machine is modest too: one unit on a shelf in the practice office, specified for the number of staff who will use it. We shortlist candidates, install the machine, import the policies folder and the letter templates, and test the shortlist against them before settling on one.
Around the model sit the tools the office actually touches: a private chat assistant for drafting, document spaces that answer “where is our radiation protection file and when was it reviewed?” with the page cited, and a custom assistant for the monthly compliance check. Sign-in is the Microsoft 365 or Google Workspace account staff already have.
What the model never sees is the clinical record. It is not connected to the practice management system, it is not for radiographs or diagnosis, and it is not a medical device. Model upgrades are made with the practice manager as part of support, so the drafts the office has come to rely on do not change without warning.
The Model Is the Engine. This Is the Car.
A bare model is a demo. Dental practices need the machine, the tools around the model, the sign-in and someone to maintain it.
A model matched to the work
An open-weight local LLM chosen and tested against your own documents, on a machine specified to run it well for your team size.
Document spaces around it
The model on its own answers from what you paste in. Spaces let it search, summarise and compare across hundreds of your files, citing the page each answer came from.
Chat and assistants on top
A private chat assistant for the team and custom assistants for the recurring jobs, all running on the same machine as the model.
| Document | What the practice asks for | What stays where |
|---|---|---|
| Referral letters and replies | Draft the referral; summarise what came back | On the machine, in the practice |
| Treatment plan and recall letters | Draft in the practice’s wording from the plan | On the machine, in the practice |
| Complaints | Draft a response from the file and your complaints policy | On the machine, in the practice |
| Policies, SOPs, audits, training records | Find it, check the review date, cite the page | On the machine, in the practice |
| Supplier and lab contracts | Compare terms, flag the differences | On the machine, in the practice |
| Clinical records and radiographs | Not used — stays in the practice system | Your practice management software |
From Practice Manager’s Call to a Model in the Office
Weeks, not months. Most practices start with the policies folder or the referral correspondence and widen from there.
A call with the practice manager
NHS, private or mixed, how many staff, which paperwork goes first. We specify the machine from that.
Install and import
The machine goes on the practice network. Sign-in connects to your Microsoft 365 or Google Workspace. Policies, SOPs and correspondence are imported into spaces.
Train the team, then support
We train the practice manager and reception first, then keep the software and models current, with support 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 is not a frontier model
The largest cloud models are still ahead of any local LLM on hard, novel reasoning. If your work needs that, a local model is the wrong tool and we will say so. For summarising, drafting and answering questions about your own documents, most offices are happy with it.
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.
We Run Our Own
Chosen against your files
Model selection is tested on a sample of your own documents, not a public leaderboard.
Sized with the model
The machine and the model are specified together. A model the hardware cannot run well is the commonest DIY mistake.
Upgrades made on purpose
Model upgrades are part of support, so someone is deciding when the answers your team relies on are allowed to change.
UK data protection built in
No third-party AI processor and no restricted transfer for the AI step. UK GDPR, the Data Protection Act 2018 and the ICO as regulator, with a data processing agreement for the support access you grant us.
Which Page Answers Your Practice’s Question
| If your question is… | The short answer | Read more |
|---|---|---|
| How is the model chosen in general? | Tested against your documents, not a leaderboard | Local LLM |
| We want the Local AI overview for dentists | The head page for dental practices | Local AI for dental practices |
| What exactly is installed in the practice? | One machine in the office, supported | On-Premises AI for dental practices |
| Our data protection lead needs the data flow | No processor, no transfer, for the AI step | GDPR Compliant AI for dental practices |
| We also need the phone answered | A hosted agent, live in days | AI Receptionist |
| We are a GP practice, not dental | A model in the surgery office, managed | Local LLM for gp practices |
| Why on-premises at all? | The case for Local AI, in full | Local AI product page |
Local LLMs for Dentists: Common Questions
What is a local LLM?
A large language model — the kind of model behind chat assistants — running on hardware you control rather than accessed through a provider’s service. Your prompts, uploaded documents and chat history stay on that machine in the practice.
Which local LLM models do you install?
It depends on the job. Drafting and summarising, answering questions across a document library, and structured extraction each favour different open-weight models, and the machine has to fit the model. We shortlist and test candidates against a sample of your own documents during setup.
Do we need to understand the model to use it?
No. The practice manager sees a chat assistant and a set of document spaces; the model behind them is chosen, installed and kept current by us. If a model upgrade is due we discuss it with you first, because it can change how drafts read.
Which local LLM models suit a dental practice?
Ones that write plain, careful English and find the right passage in a policy folder reliably. The practice’s document set is modest, so the model and the machine can be too. We test the shortlist against your own letters and policies before settling on one.
Does it connect to our practice management software?
No, and that is deliberate. The clinical record stays in your practice system. It works on the documents around it — letters, policies, correspondence, contracts — which are imported into document spaces on the machine.
Can it read clinical photographs or radiographs?
The private chat accepts images, but we advise against using it for anything clinical. It is for the practice’s administrative documents. Diagnosis and treatment decisions stay with the clinician.
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.
Let the Model Be Our Problem
Tell us which paperwork takes the office longest and whether you are NHS, private or mixed. One short call to choose the model and size the machine.
Prefer email? sghaith@businessaiagents.co.uk