A private AI workspace for funeral homes

Families come to you at their most vulnerable, and the details they share are the last thing you want passing through a public cloud. A name, a cause of death, a falling-out between relatives, the wishes whispered across your desk: this is information people trust you to hold quietly.

The moment any of it gets pasted into a public chatbot, it leaves your building and lands on servers you do not control, often in another country. There is a better way to give your team capable AI while that grief stays on your side of the door.

Why a public chatbot and grieving families do not mix

A public AI chatbot is a remote service. Whatever your staff type into it travels to a company you have no agreement with, gets stored on hardware you cannot see, and is frequently held in a US cloud. For a funeral home, that is the wrong place for a bereaved family's most private moments.

The instinct is to ban it. That instinct fails, because your people already use it. The arrangement coordinator who needs a kinder way to word a difficult letter, the director drafting an obituary at the end of a long day: they reach for whatever tool is open in the browser. A ban just pushes that use somewhere you cannot see. The answer is not less AI. It is AI that stays in the building.

Run the model in-house

With kral, the platform runs on your own server. You can add a local model on your own hardware, so a prompt about a named family goes to your machine and stops there, with no external API anywhere in the path. The text never leaves the room it was written in.

Most homes mix the two. A cloud model handles the general work where nothing private is in play, and a local model takes the sensitive cases, the ones with a real family's name and circumstances attached. You decide which prompt goes where, and the line is yours to draw.

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. One can draft sensitive family communications, turning a few notes into a letter that reads with care instead of a blank page at the worst moment. Another can take the details of an arrangement and turn them into a clear checklist, so nothing for the service slips.

You can save reusable routines so nobody rebuilds the same setup twice. Drop in a document and ask questions about it. Pull a current, cited answer from the web when you need a fact you can stand behind. And switch between the leading models in one click, picking the right one for the task in front of you.

Connect your own systems

kral supports MCP, the open standard for connecting tools and data to an AI. That means the assistant can work with your own templates and your internal knowledge through a connector you control, instead of guessing from the open web. It answers from how your home actually does things. Your systems stay yours, and nothing is handed to an outside service to make the connection work.

You run it and you see everything

You manage who is in and which models each person can use. Set a spending limit per person so costs never drift. Watch real usage on a dashboard. Sign-on is single sign-on, so staff use the login they already have. It installs on Windows Server behind IIS, sits inside your network behind your firewall, and wears your own branding. For a broader look at the same idea, see this guide to company-wide AI you host yourself.

We help you put it in place

You do not have to do this alone. We set kral up with you, connect it to your systems, and advise on rolling AI out to your team without the data leaving your side. Implementation consulting is part of what we offer, so the move from a public chatbot to something you own is one we make with you, step by step.

Your families trust you with the details of their hardest days. Give your team a capable AI that honors that trust by keeping it on your server, where it belongs.

Book a demo

Open the app