A company AI assistant that cites its sources
An AI assistant inside a company is only worth what it knows, and what it admits it doesn't know. Here is how ours works, from the moment the day starts to the question it can't settle.
Published on 28 August 2026
It opens the day before you ask
In the morning, the assistant has already written up what's waiting: the day's meetings, the news that concerns you and that you haven't read yet, the answers that have come back on your requests, the client files that are pressing, the ones running late. The text is short and reads in ten seconds.
Every item in it is clickable: the file mentioned opens, the news item is marked as read without leaving the page. This daily briefing is only regenerated when the facts change, which costs a few cents per person per day instead of a charge every time someone opens it.
It answers the way the office next door would
The question is asked in plain language. Before searching, the assistant works out what it is about: if the subject is named, it sticks to it; if it is torn between two pieces of software, it asks rather than guesses. Then it searches the connected documentation and the company's memory, and it answers citing its source with the link.
It also goes and looks at live data when the question calls for it: your diary, the client files in your scope, the news, your open requests. A team member never sees a client file that isn't theirs, and neither does the assistant: scope is checked on the server, not in the instruction given to the model.
It says when it doesn't know
This is the one point we will not compromise on. An assistant that invents a procedure wastes more time than it saves, and it destroys trust in a single answer.
When the answer exists nowhere, the question does not die for all that: it goes to your in-house expert, to your IT person, or to the software vendor's support, depending on what makes sense. It becomes a tracked request, and its answer joins the knowledge base.
It points you to the right person
Some questions need a human. The assistant knows who on the team has already handled a similar case, and says so. Whatever someone has approved as an answer becomes visible on their profile, under "What they've shared with the team".
What it doesn't do
It doesn't decide for you and it signs nothing. No reply to a client goes out without a human having read and approved it. It doesn't replace the expert-comptable (chartered accountant), the lawyer or the IT specialist: it takes off their hands the questions whose answer already existed.