Use case

Marketing

A designer puts the logo on a dark background and asks whether blue is allowed. A copywriter wrote “the best and unique service, free forever” — and did not check it against the “How we talk about the product” document. The brand book is in PDF, the positioning in Word, the presentations in PowerPoint; every piece is checked by hand or not at all.

Create a knowledge space All use casesFor marketers and content managers whose brand book is a PDF, positioning a document and presentations on Drive

Situation

Brand rules are written down, but not at hand

What gets in the way

  • The brand book is a thirty-page PDF opened once a year.
  • Positioning and banned words are written down, yet texts still depart from them.
  • Presentations from past years sit on Drive, and nobody will compile a summary of them.
  • Checking material is manual and depends on one person.

Solution 01

What the brand book says — with exact values

The question: “What does the brand book say about using the logo on a dark background and its minimum size?” The AI agent reads the brand book PDF and answers: the white version only, the blue mark is not allowed, 24 px on screen and 15 mm in print — and adds the clear space and the restrictions from the same section.

How PDFs and presentations are read
Logo on a dark background

← scroll the frame →

Exact values: the white version on a dark background, no blue mark, 24 px and 15 mm, clear space — from the “Logo” section of the brand book.

Solution 02

Checking a text against the positioning document

A copywriter attaches the landing page text to a question and asks to check it against the “How we talk about the product” document. The AI agent goes through the text phrase by phrase: “the best and unique” are banned words, “free forever” is untrue — there is only a trial period, “folders” is the wrong term — and says what to add: the key difference the document says to always mention.

How to ask a good question about documents
Text against the positioning

← scroll the frame →

Table of violations: landing page phrase — what the document says — verdict, for each phrase; below, what to remove and what to add.

Solution 03

A summary of presentations — as research

“Collect every competitor comparison from our 2026 presentations into one table” — the research reads the presentations slide by slide, including speaker notes, builds the table, and the reviewer checks every row against its slide. The document goes to Drive next to the presentations.

01

Slides and notes

Presentations are read slide by slide: title, text, tables, speaker notes.

02

The reviewer checks

Every row of the summary comes with a link to the file and the slide; anything unproven is removed.

03

A question under a design

With Figma connected, the question is asked in a comment on the design, and the answer arrives there too.

A question or research?

Solution 04

Ask where people already work

A marketer asks under a design in Figma or under a text in a Google Doc — and the answer arrives there too. 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.

How to ask from a document or a ticket

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 — ad accounts, social networks — 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.

01

The connector in your network

A small program, outbound connections only by default; installed once for the whole organisation.

02

Connection to the documents

From the catalogue or a custom tool; an account that can read and comment, with the marked sections and folders.

03

The department’s space

Access is granted per space: the marketing space has no access to the finance documents until the owner grants it.

What to ask your administrator for

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 write or publish posts

it checks and answers from your documents.

There are no ad accounts or social networks in the catalogue

if needed, they are connected with a custom tool.

Images are not read

the text of the brand book and slides is read, the logo artwork and charts themselves are not.

Outcome

The designer and the copywriter check against the brand book and the positioning themselves, in a minute and with a quote, and summaries of past years’ materials are compiled as a document, not by hand.

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