A private AI workspace for your dental practice

Imagine pasting a patient history into a free chatbot to speed up a recall letter, and that history now sits on a server the practice has no agreement with. The name, the date of birth, the treatment notes: all of it copied somewhere you will never get it back from, processed by a company you have no contract with, on hardware in another country.

That one paste is the quiet risk in most practices today. The good news is you do not have to choose between useful AI and keeping records on your side. You can have a capable assistant that runs on your own machine, so the sensitive cases never leave the building.

Why a public cloud chatbot clashes with dental practices

A patient record is some of the most personal data a practice holds. Medical history, medication, contact details, notes a patient told you in confidence. The moment that text goes into a public chatbot, it lands on infrastructure you do not own and cannot inspect, often in a US cloud. You have no agreement covering it and no way to delete it later. For a practice that is responsible for keeping that information safe, that is a hard problem.

Banning AI outright does not solve it. Your staff already use it. A receptionist pastes a query to phrase a difficult letter, a hygienist asks a chatbot to summarise a long note. People reach for tools that make their day easier, and a memo telling them to stop just pushes it out of sight. The answer is to give them something better that you control.

Run the model in-house

With kral the whole platform runs on your own server. You can also add a local model on your own hardware, so a prompt about a named patient goes to your machine and stops there. There is no external API in the path for those requests. The data does not travel.

Most practices run a mix. A strong cloud model handles the general work where no patient is named: drafting a newsletter, rewriting a supplier email, brainstorming a campaign. A local model handles the sensitive cases, where a real record is involved. You decide which goes where, and the line is clear to everyone on the team.

A full workspace, not a chat box

This is more than a single chat window. Your team can build their own assistants in minutes with no code. One assistant drafts recall and treatment-plan letters in your tone, so a reminder that used to take ten minutes takes one and still sounds like your practice. Another turns rough chair-side notes into a clean, structured record, ready to file. You save reusable routines so nobody rebuilds the same setup twice, and the next person inherits a working tool instead of a blank page.

You can drop in a document and ask questions about it, pull a current answer from the web with its sources cited, and switch between the leading models in one click when a task needs a different strength. It is one place for the practice to work, not a browser tab everyone improvises in.

Connect your own systems

kral supports MCP, the open standard for connecting tools and data to an AI. Through a connector you control, the assistant works with your own letter templates and your internal knowledge instead of guessing from the open web. The recall letter follows your wording, not a generic one. Your systems stay yours, and the connection runs on your terms.

You run it and you see everything

You manage who is in and which models each person can use. You set a spending limit per person, so costs never run away from you, and you watch real usage on a dashboard. Staff sign in with single sign-on, so there is one login to manage and nothing extra to hand out. kral installs on Windows Server behind IIS, sits inside your network behind your firewall, and wears your own branding. It looks and behaves like part of the practice, because it is. For the wider picture on hosting this yourself, see company-wide AI you host yourself.

We help you put it in place

You do not have to work this out alone. We set kral up with you, connect it to your systems, and advise on rolling AI out across the practice without the data leaving your side. Implementation consulting is part of what we offer, so the result is a working setup your team actually uses, not software left in a folder.

Useful AI and patient confidentiality are not opposites. Run the model on your own server, keep the sensitive cases local, and give your team a tool they will reach for instead of the public chatbot. That is the whole point.

Book a demo

Open the app