A big smiling robot in front of a wall of toy cars. Its speech bubble holds three toy cars.

Ask
Again

A simple guide to what AI says
about your business

Dmitrij ŻatuchinFOUNDER & CEO • RANKFOR.AI

Free illustrated book 88 pages

A free book by Dmitrij Żatuchin. Each chapter tells one study on AI answers as a short story, with one step to try on Monday. Each chapter page ends with its reference: a link to the paper or its data.

Every chapter is free to read here, with no sign-up. For the PDF, give your email address and the download link arrives by email.

Why I wrote this

My children are 9 and 12. They wanted to know what research I do and what my book is about.

So I tried to explain it in a way they could understand. This book is the result.

If you run a business, it is for you too. Your customers can now ask AI which company to choose. It could be a pizzeria, an accountant, a lawyer, an online shop, a media agency, a publisher, a car dealer or a company that builds and sells homes. You will want to know what the answer says.

In this book I call AI assistants robots. ChatGPT, Gemini and Perplexity are all robots here.

Each chapter starts with a short story, explains a finding from research and gives you one thing to try on Monday. The references at the back link to the studies. A short glossary explains a few useful words.

Please open those links. I founded Rankfor.AI and I run it. We sell businesses tools that measure what the robots say, content written for them to read, and publishing where they read it. We also help publishers sell sponsored content. I sell a book on this subject too. So I earn money when businesses care about these answers. Keep that in mind as you read.

We do not promise a place in their answers.

Dmitrij Żatuchin
Tallinn, November 2026

The people in this book

You will meet eight business owners here. I made them up, so their stories are examples. The numbers come from the studies, and each chapter says what was measured.

The pictures make the numbers easier to see: pizzas, cars, houses, parcels, books and more.

Portrait of Javier, a man with short black hair in a green shirt.Javier MoralesPizzeria owner, Spain
Portrait of Giulia, a woman with her hair in a bun, wearing a black jacket and a green earring.Giulia RomanoAccountant, Italy
Portrait of Daniel, a man with a short black beard in a dark suit.Daniel MensahLawyer, Germany
Portrait of Marta, a woman with dark shoulder-length hair in a black jacket.Marta KowalczykOnline shop owner, Poland
Portrait of Samira, a woman with simple dark hair in a black jacket.Samira BenaliMedia agency founder, France
Portrait of Joost, a bald man with a white beard in a pale green jacket.Joost BakkerPublisher, the Netherlands
Portrait of Mikko, a man with round glasses and a red-brown beard in a green sweater.Mikko VirtanenCar dealer, Finland
Portrait of Kadri, a woman with a long brown braid in a green hoodie.Kadri TammBuilds and sells homes, Estonia

You will also meet these two in the pictures.

A friendly robot with a screen for a face.The robotAny AI assistant
Portrait of the author, a man with short brown hair and a grey goatee in a black T-shirt.MeThe one with the clipboard

A few useful words

AI
Software that can do some tasks people do, like writing or spotting patterns.
Average
Add all the numbers, then divide by how many you have.
Brand
The name and look that help people know a firm or product.
Data set
A group of records kept for a study or test.
DOI
A fixed code that helps you find a paper or data set.
GEO (Generative Engine Optimization)
Trying to help a firm get named in AI answers.
Large language model (LLM)
A kind of AI trained on lots of text to write more text.
Peer-reviewed
Other experts checked the study before it came out in a journal.
Persona
A made-up shopper with needs and questions you can think about.
Preprint
A paper shared online before it appears in a journal. It may never appear in one.
Prompt
What you ask an AI to do or answer.
Tone score
A program’s number for text it reads as positive, neutral or negative.
Version
One form of a paper, data set or robot’s software.
Looking on the web for pages to help answer a question.
Wobble
How much a count changes when you ask again.

Part One

Ask again: how answers repeat and change

Part Two

What ends up in the answer: links, people and names

Part Three

One word, one language: how the question changes the answer

Part Four

Before you believe a number

Questions

Is the book free?

Yes. Every chapter is free to read on this site. The PDF is free too: give your email address and the download link arrives by email.

Who is it for?

Dmitrij wrote it for his children, who are 9 and 12. It is also for anyone who runs a business and wants to know what AI assistants say about companies.

Why does the book call AI assistants robots?

To keep it simple. In this book ChatGPT, Gemini and Perplexity are all called robots.

Where do the numbers come from?

From the studies the chapters describe. Each chapter page ends with its reference from the back of the book. It links to the paper or its data and says what kind of source it is, such as a journal article, a preprint or a data set.

Does Rankfor.AI sell anything linked to this?

Yes. Rankfor.AI sells businesses tools that measure what the robots say, content written for them to read, and publishing where they read it. It also helps publishers sell sponsored content. Dmitrij also sells a book on this subject. Rankfor.AI does not promise a place in AI answers.

Keep asking

I started this book because my children wanted to understand what I was working on. You have met robots choosing toys, naming companies and filling boxes with pretend shoppers. Behind those pictures is a question a business owner can ask: “What would a customer hear about us?”

You can begin with a question a customer has already asked you. Put it to a robot. Read the answer. Ask again in a fresh chat, then try another robot. Keep the answers, so you can compare them.

Look at the names. Who keeps coming up? Who did you leave out of your own list? Read the reasons too. If a report gives you a score, open the answers behind it and see what was counted.

Then choose something useful to work on. Perhaps your website makes it hard to tell what you sell. Perhaps an answer repeats an old fact. Make the information clear and correct, and come back to the same questions to see what changed.

My children started this with their questions. I hope the book gives you a few of your own.

Pick a question that matters to your customers. Keep asking, and keep reading the answers.

About me

Photograph of Dmitrij Żatuchin, smiling, in a black T-shirt.The real me
Dmitrij drawn in the style of this book.The me in the pictures

I am Dmitrij Żatuchin. For more than twenty years I have built technology companies. I also do research, and I teach.

I founded Rankfor.AI and I run it. There I study how AI assistants describe and name companies, and I work with marketing teams on what to do with those findings.

Before that I founded and led DO OK, a software services company with a team of around sixty people. It was listed on Poland’s NewConnect market and recognised in Deloitte’s Technology Fast 50 Central Europe. I also co-founded SoDA, Poland’s association of IT services employers.

I hold a PhD in computer science from Wrocław University of Technology. I was a lecturer and researcher at the Estonian Entrepreneurship University of Applied Sciences, and I led the Data-Based Decision Making and Leadership microdegree at Estonian Business School. I have been teaching business owners about AI visibility across the Baltics, Finland and Poland.

My book, Become the Answer, tells this story for marketing teams.

I live in Tallinn with my wife and two children, whose questions started this book.

Did you try the Monday steps? Tell me what you found.

More about Dmitrij

References

Chapter 1. Robots make a list, and you can check it

Peer-reviewed, journal version (paid access). Dmitrij Żatuchin (2026). The synthesised consideration set: brand inclusion and concentration in large language model recommendations across five industries and three systems. Journal of Marketing Analytics, published online 31 October 2026. 10.1057/s41270-026-00562-3.

Free preprint. arXiv:2606.23057. Data, version 3.0. 10.5281/zenodo.22927143.

Chapter 2. Ask robots for lottery numbers, and tickets repeat

Preprint. Dmitrij Żatuchin (2026). Ask a Language Model for Lottery Numbers: Concentration in Repeated Six-of-49 Outputs. arXiv:2610.00052, version 1. arXiv:2610.00052v1. Data and code. github.com/Rankfor/rankfor-open/tree/main/research/lotto-models.

Chapter 3. One answer misses names, so ask again

Preprint. Dmitrij Żatuchin (2026). Measuring Brand and Source Discovery under Repeated LLM Queries: A Finite-Sample Audit. arXiv preprint, version 2, September 2026. arXiv:2609.05059v2.

Chapter 4. No single number of tries fits every question

Preprint. Dmitrij Żatuchin (2026). The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations. arXiv:2609.04047, version 2, 14 October 2026. arXiv:2609.04047v2. Data. 10.5281/zenodo.22927143. Gift answers are listed in chapter 12.

Chapter 5. One robot’s named companies barely changed in 20 days

Preprint. Dmitrij Żatuchin (2026). Twenty Days Later: A Pre-Registered Test of History-Based Forecasts of Brand Mentions in Gemini Answers. arXiv preprint, version 1, 14 October 2026. arXiv:2610.19608. Data. 10.5281/zenodo.23351313. Register entry. osf.io/x8h3p.

Chapter 6. A small share of websites got most robot links

Preprint. Dmitrij Żatuchin (2026). How Large Language Models Source Brand Reputation Across Languages and Markets. arXiv:2606.25787. Data, version 1. 10.5281/zenodo.20829524.

Chapter 7. About one answer in four named a person

Preprint. Dmitrij Żatuchin (2026). Who Gets Named: Citation Type Predicts Individual Naming by Grounded Language Models, and a Roster Instrument Captures 0.5% of It. arXiv preprint, version 2, 1 August 2026. arXiv:2607.23893.

Chapter 8. Made-up firms with gloomy names got gloomier words

Data set. Dmitrij Żatuchin (2026). Does an AI describe your company, or your company’s name? 9,600 model answers about invented and real European firms. Version 1.0, 12 August 2026. 10.5281/zenodo.21904654.

Chapter 9. A tone score changed more with language than company

Revised manuscript. Dmitrij Żatuchin (2026). Query Language Sensitivity in Automated Sentiment Scores of LLM Responses. Original preprint. arXiv:2607.13304v1. Related aggregate data. 10.5281/zenodo.20794390.

Chapter 10. When language and place both changed, the names changed

Preprint. Dmitrij Żatuchin (2026). The Language Blind Spot: How Query Language and Brand Recognition Tier Shape AI-Constructed Brand Reputation Across Twelve European Languages. arXiv:2606.23165. Data. 10.5281/zenodo.20794390.

Chapter 11. Same question, other language, other names

Revised manuscript. Dmitrij Żatuchin (2026). Query Language and Network Exit Context in Generated Supplier Mentions: An Exploratory Audit. Original preprint. arXiv:2608.30052v1. Raw records. 10.5281/zenodo.22181306.

Chapter 12. Gift lists differed for husband and wife

Data for the reanalysis. Dmitrij Żatuchin (2026). Supplementary Materials: Volume and Distribution as Separable Dimensions of Gender Bias in Large Language Model Brand Recommendation. Zenodo, version 1.0. 10.5281/zenodo.21904788.

Chapter 13. One count can fool you. Mine did.

Data for the reanalysis. Dmitrij Żatuchin (2026). Supplementary Materials: Volume and Distribution as Separable Dimensions of Gender Bias in Large Language Model Brand Recommendation. Zenodo, version 1.0. 10.5281/zenodo.21904788.

Chapter 14. A robot’s report card can flip with the question

Preprint. Dmitrij Żatuchin (2026). System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer. arXiv, version 1. arXiv:2610.00253. Data. 574 of the gift answers are at 10.5281/zenodo.21904788.

Chapter 15. Robots share a taste for robot writing

Peer-reviewed original study, open access, CC BY 4.0. Walter Laurito, Benjamin Davis, Peli Grietzer, Tomáš Gavenčiak, Ada Böhm and Jan Kulveit (2025). AI-AI bias: Large language models favor communications generated by large language models. Proceedings of the National Academy of Sciences 122(31), e2415697122. 10.1073/pnas.2415697122. Code and run files. github.com/lauritowal/ai-ai-bias.

Preprint, reanalysis. Dmitrij Żatuchin (2026). A Shared Taste for Model-Written Text: The Generator-by-Selector Matrices of “AI-AI Bias” Show No Detectable Own-Model Premium. arXiv:2610.00369. The same paper is on SSRN: 10.2139/ssrn.7514779. The reanalysis and its reading of the original data are Żatuchin’s.

The pictures are my drawings, using the original authors’ numbers.

Chapter 16. Pretend shoppers give you questions to try

Preprint. Dmitrij Żatuchin and Daniil Dzemesjuk (2026). Demand-Side Measurement for Generative Engine Optimization: Constructing and Validating a Million-Persona, Intent-Annotated Buyer Corpus. arXiv:2608.30023, version 1, 30 August 2026. arXiv:2608.30023.

Public sample. PersonaGen-15K, 14,955 pretend shoppers. huggingface.co/datasets/rankfor/PersonaGen-15K. Research use only, CC BY-NC-SA 4.0.

What does AI say about your business?

Put the book into practice. Tell us your company and website to request an AI visibility audit. We’ll reply by email to agree what to check.

What the audit shows

  • Where your company appears in the answers, and next to whom
  • The pages AI cites in your market
  • What to publish first on your own site

Fields marked * are required.

Who is it for?

Your choice about cookies

We use cookies this site needs to work, and others only if you say yes. Choose what you allow, and change your answer whenever you like. Read our privacy policy