Use case
Sales
A new manager is preparing a proposal and does not know what terms similar clients got, what volume discount applies, or whether the standard contract renews automatically. A senior manager remembers roughly, and the contracts sit in the “Contracts” folder — forty PDF files with a text layer; scans without text would have to be recognised in advance, in the scanning software or by IT.
Situation
Deal terms live in contracts, not in people’s heads
What gets in the way
- Payment terms and deferrals of past deals are scattered across contracts and commercial proposals.
- Only those who wrote the discount policy know it by heart.
- Three versions of one proposal — and nobody remembers how they differed.
- The question “what did we promise in the contract” goes to a lawyer and waits until tomorrow.
Solution 01
Terms of past deals — in a table, with contracts and managers
The head of sales asks what payment terms, deferrals and discounts clients in the “distribution” segment got in 2026, and asks for a table. The AI agent reads the deal register, the contracts and the proposals and answers with a table: client, contract, payment terms and deferral, discount, manager — and below, checks the register against the contract and the discount policy.
About “Ask”← scroll the frame →
Solution 02
A contract clause — word for word, with a caveat about exceptions
A manager asks whether the standard subscription contract has an automatic renewal clause and what the notice period is. The AI agent quotes section 9 of the template — 30 days to opt out of renewal, 60 for a price change — and warns that the period may differ in signed contracts, naming which ones.
How to ask a good question about documents← scroll the frame →
Solution 03
Price list and volume discount — from the spreadsheet, not from memory
How much is the “Business” plan per seat per year, and what discount does a client with 80 seats get? The AI agent reads the price list sheet by sheet and the discount policy: price per seat, volume discount, who approves a larger discount — all with the name of the sheet and the document.
How spreadsheets and folders are read← scroll the frame →
Solution 04
Comparing proposal versions — as a document
When you need a document for the head rather than an answer — for example, a comparison of three versions of a proposal for one client by price, discount, term and scope — you order research: the analyst reads the versions and writes the comparison, the reviewer checks every figure against the documents. The document is exported to PDF or appears on Drive next to the proposal.
The analyst writes
Builds the comparison from three proposal versions and the discount policy; every figure comes with a link to the file.
The reviewer checks
Rereads the documents, finds what is unproven and where they disagree, and raises remarks.
The document goes to you
A PDF or a text file; ordered from Google Drive, it arrives as a new document in the same folder.
Solution 05
Ask where people already work
A manager asks under a commercial proposal in a Google Doc — 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 06
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 — CRM, telephony, email — 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 sales space has no access to the legal documents until the owner grants it.
Solution 07
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 send emails or create proposals from a template
it prepares the answer and the comparison; a person writes.
There is no CRM in the catalogue
your IT specialist connects Bitrix24 or amoCRM with a custom tool, after which the client history is read just like the documents.
Contract scans without a text layer are not read
the product has no text recognition; scans are recognised beforehand by your scanning software or by IT.
Outcome
The terms of any past deal, a clause of any contract and the discount from the price list — in a minute, with a link to the document. A new manager answers a client as confidently as a senior one.
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