Use case
Head of department
The project board meets on Thursday. What was decided in July, what was postponed in August, what remained open in September — it is all in three sets of minutes. The month’s reports from three departments give different figures for the same thing. There is no time to reread the quarter.
Situation
To answer “what did we decide”, you have to reread the quarter
What gets in the way
- Decisions and open questions are scattered across meeting minutes.
- Department reports contradict each other, and nobody reconciles them before the meeting.
- A postponed question moves from minutes to minutes until it is forgotten.
- An assistant compiles the summary for the board — half a day’s work.
Solution 01
Decisions over the quarter and what remained open
The question: “What decisions on the ‘Mobile app’ project were made at meetings in the third quarter, and which questions remained open?” The AI agent reads three sets of minutes and answers meeting by meeting: decisions, open questions, what was postponed — and separately notes a question postponed for the second month and a decision that reversed the July one.
About “Ask”← scroll the frame →
Solution 02
Discrepancies between department reports
The question: “Pull together the key figures from the support, sales and marketing reports for September and name where the reports disagree.” The AI agent reads the three reports, brings the figures together and names two discrepancies — the number of requests about the export bug and the number of leads passed from marketing to sales — before anyone notices them at the meeting.
A question or research?← scroll the frame →
Solution 03
What the head sees in the workspace
The organisation’s audit log and billing history show who asked questions and when, how much each space and project spent, and which connections are working. The organisation owner sees them; a department head can be given a separate right to read the log without being made an owner.
Audit log
Who did what, when and from where — filtered by section and exportable in full; the text of the questions does not go into the log.
Read-only access
The head reads the department’s space and its knowledge base without changing anything in them.
← scroll the frame →
Solution 04
Ask where people already work
The head asks under the meeting minutes in Notion — and the answer arrives as a comment on them. A comment on a Notion or Confluence page, in a Google Doc, on a Figma design or in a tracker ticket that mentions the AI agent is a question, and the answer arrives in the same discussion. Research is ordered the same way: the finished document appears next to the original. There is no need to open the app.
In the app
The “Ask” section of the space: question, answer and follow-ups, like a conversation; the price of the question is shown right after the answer.
In a comment on a document
Notion, Confluence, a Google Doc or a Figma design: a mention of the AI agent in a comment is a question, and the answer arrives in the same thread.
In a tracker ticket
Jira, Redmine and others: a question as a comment, an answer as a comment; research arrives as an attached document.
Solution 05
What your IT specialist does — once
Installs the connector in the company network, picks a connection from the catalogue — Notion, Confluence, Google Drive, folders on a server, a tracker — names the department’s space and marks which sections and folders to read. Systems outside the catalogue — calendar, messengers — are connected with a custom tool: separate IT work following our documentation, after which the system is available to the AI agent just like the catalogue. From then on the department works on its own; a file that is not in the sources is simply attached to the question.
The connector in your network
A small program, outbound connections only by default; installed once for the whole organisation.
Connection to the documents
From the catalogue or a custom tool; an account that can read and comment, with the marked sections and folders.
The department’s space
Access is granted per space: the management space has no access to the HR documents until the owner grants it.
Solution 06
What the AI agent does not do
The limits are stated up front, so the department does not wait for what will not come.
Does not assign tasks or set work for employees
it answers from minutes and reports.
There are no calendars or messengers in the catalogue
your IT specialist connects them with a custom tool.
Does not assess people or draw conclusions beyond the documents
the discrepancy is named; the decision is yours.
Outcome
The summary for the board is put together with a question, not half a day of an assistant’s work; postponed questions and discrepancies between reports are visible before the meeting, not after.
The first step is a name
Create a space and ask your first question
Sign up by email and the space is ready at once. Until your IT specialist connects the documents, the AI agent answers from the knowledge base and from files you attach to the question. A starting balance is provided to try it out.
Until documents are connected, attach a file to the question