Use case
Legal and contracts
A colleague asks: “What about our contract with sole trader Kungur — when does it expire and what are the penalties?” The contract is in the folder; the lawyer opens the PDF and scrolls to section 6. An hour later comes a question about the procurement policy: “What changed in the new edition?” Two documents of thirty clauses each, to be compared by hand.
Situation
Hundreds of contracts — and every question means opening a file
What gets in the way
- Contracts in PDF and Word on a network drive: answering a simple question means finding and opening the file.
- Policies exist in several editions, and colleagues read the old one.
- The question “which contracts have penalties and at what rates” means going through the whole folder by hand.
- The lawyer answers the same questions instead of working on contracts.
Solution 01
A contract from the folder — number, subject, term, liability
The question: “What is the number of the contract with sole trader Kungur, what does it cover and until when is it valid?” The AI agent finds the file in the network folder, reads the PDF and answers section by section: subject, price and payment procedure, penalties, closing documents, term — with the path to the file.
Folders and network drives as a source← scroll the frame →
Solution 02
Two editions of a policy — the difference as a table
The question: “How does the 2026 edition of the procurement policy differ from the 2024 edition in approvals and supplier selection?” The AI agent reads both editions and answers with two tables: approval thresholds, method and timing, the number of supplier offers — and separately names the new clauses: legal review of contracts with auto-renewal and a personal data check.
How to ask a good question about documents← scroll the frame →
Solution 03
Going through the whole folder — as research
“Build a table of all 2026 contracts — counterparty, term, payment, penalties, closing documents — and check them against the standard template and the deal register” is not one document but the whole folder. The research reads the contracts one by one, builds the table, checks it against the template and the register, and the reviewer rereads the contracts and removes anything unproven. The result is a PDF document you can attach to an internal memo: in 9 minutes and for 30 ₽ in the demo workspace.
A question or research?← scroll the frame →
Solution 04
Ask where people already work
A colleague asks under the policy page in the wiki — and the answer arrives as a comment on it. 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 — document management system, 1C — 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 legal 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 edit documents or draft contracts
it only reads and answers.
Scans without a text layer are not read
the AI agent will name such a file as unreadable; there is no text recognition.
Personal data in contracts
a matter of the plan: on OpenRouter plans the text is read by a third-party provider’s models; on dedicated capacity and in a custom setup it does not go to a provider, and within Russian jurisdiction it stays on dedicated capacity in Russia or in a custom setup (on request).
Outcome
Colleagues get an answer about a contract with a link to the file without a lawyer, the lawyer compares editions in a minute, and going through the contracts folder becomes a document instead of a day’s work.
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