Implementations

It usually starts with one thing: the assistant answers questions from your company documents and shows which document the answer came from. The other two pages say what that depends on — where those documents reach it from, and where all of it sits. Sometimes you already have both, and we start straight with the assistant. Each of them can be ordered on its own.

Flow: documents from mail, the shop and the invoicing program reach the assistant, which answers and names the document the answer came from. All of it runs on the company hardware. — Documents come in from places you already use. The assistant answers and shows the source. All of it runs where we agree.

Find answers in company documents — and check the source
What you actually get: you ask in a plain sentence and get the answer along with the document it came from.
Data should not get stuck between programs
Where the assistant gets the documents — and why nobody retypes them from one program into another. Can be ordered on its own, including when you have no use for an assistant but the retyping still eats your time.
A home for your company data — and a message when something stops
Where all of it sits and whose it is. You can start here, add it later, or skip it entirely if the hardware you have is enough.

Implementations

Find answers in company documents — and check the source

Data should not get stuck between programs

A home for your company data — and a message when something stops