A private AI workspace for care homes

A resident care file is one of the most personal documents a family ever trusts to anyone, and a free chatbot would send it straight out of the building. The moment a staff member pastes a name, a diagnosis, a next of kin, or a safeguarding note into a public tool, that record has left your care and landed on a server you do not run.

It does not have to work that way. A capable AI can sit on your own server, inside your own network, and answer the same questions while the resident and family records stay on your side. That is the whole idea behind kral, and the rest of this page shows you how it holds together.

Why a public cloud chatbot clashes with a care home

Care work runs on detail that should never be shared casually. Medical histories, family disputes, end of life wishes, financial arrangements, incident reports. A public chatbot is a US cloud service: anything typed into it travels out of the home, gets processed somewhere you cannot point to, and may be retained for reasons you have no say in. For the kind of records a care home holds, that is the wrong default.

The instinct is to ban it. That instinct fails. Your staff are already using AI on their phones to draft letters, summarise notes, and word difficult messages to families, because it genuinely saves them time on a busy shift. A ban just pushes that use somewhere you cannot see. The better move is to give them a tool that is just as quick and keeps the data where it belongs.

Run the model in-house

With kral the platform runs on your own server. From there you have a choice for every prompt. You can add a local model on your own hardware, so a question about a named resident goes to your machine and stops there. No external API sits in that path. The text never leaves the building.

Most homes run a mix. A cloud model handles the general work where nothing sensitive is involved: a policy summary, a rota explanation, a plain rewrite. The local model handles the sensitive cases, the ones with real people in them. Same workspace, same single window for staff. You decide which model each piece of work goes to.

A full workspace, not a chat box

This is more than a place to type a question. Your team can build their own assistants in minutes with no code. Set up an assistant that drafts family update letters in your tone, so a monthly note home takes two minutes instead of twenty. Build another that turns rough shift notes into a clean handover the next staff member can actually read. Save those as reusable routines, so nobody on the team rebuilds the same setup from scratch every week.

Staff can drop in a document and ask questions about it directly. They can pull a current, cited answer from the web when they need something factual. And they can switch between the leading models in one click when one suits the task better than another. It feels like one tool, not a dozen tabs.

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 can work with your own care plan templates, your own internal guidance, your own way of writing things, instead of guessing from the open web. You point it at the knowledge you already trust. 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. You watch real usage on a dashboard and know exactly what is happening. Staff sign in with single sign-on, the same login they already have. It installs on Windows Server behind IIS, sits inside your network behind your firewall, and wears your own branding so it looks like part of the home. This is the same approach behind any company-wide AI you host yourself: capable tools, kept on your infrastructure, under your control.

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 home without the data leaving your side. Implementation consulting is part of what we offer, so the technical side does not land on your manager or your one IT contact. You get a working setup and people who know how to make it fit a care home.

Your staff want to use AI, and that is fine. The question is only where the data goes. Keep the resident and family records on your server, give the team a tool that is fast and genuinely useful, and you get both at once.

Book a demo

Open the app