top of page
Search

Part 4 - AI Buddy... how do you actually create an answer?

Writer: Magne Bjella
Magne Bjella
6 hours ago
4 min read

When you ask an artificial intelligence a question, you often get an answer in just a few seconds. But what actually happens from the moment you press "Send" until the answer appears on the screen? Is the answer pre-written, or is it created on the spot? In this article, we follow the journey from question to answer – step by step.



Watercolor illustration of Magne Bjella and his AI buddy sitting together at a work table in a modern and bright café or learning environment while discussing artificial intelligence, knowledge development and innovation. Both have notebooks, laptops and pens in front of them, and on the table is an open book with illustrations of a neural network, connections between information and a light bulb symbolising idea development and new insight. Next to it are books with the titles "Innovation", "Knowledge" and "People", which emphasise the connection between technology, human experience and value creation. In the background, other people are working and conversing in an open learning environment, which gives the illustration a lively feel and symbolises how knowledge is developed through collaboration, dialogue and sharing of experiences. The illustration conveys that artificial intelligence does not replace human thinking, but functions as a collaborative partner that, together with curiosity, reflection and critical thinking, can contribute to better understanding, stronger decisions and continuous learning.


Magne & the Friend


Magne


Friend...


Now you have told me how you learn, and how you try to understand what I write.


But I'm still left with one big question.


When I press "Send" and ask you something...


What's really going on?


Are you starting to look for a ready-made answer?


Or are you writing the answer while we're talking?


Watercolor illustration of the AI buddy teaching in front of a classic green chalk board, while Magne Bjella sits at a school desk and follows the lesson. The board shows step by step what happens from a question being sent to a language model until a finished answer is displayed on the screen. The illustration explains how a language model first interprets the question, activates relevant knowledge, builds the answer word by word, and at the same time maintains the theme and context of the conversation. The board emphasizes that the answer is not stored in advance, but is created in the moment through language, patterns, and probabilities. The main message is that good answers are developed dynamically through the interaction between the question and the language model's knowledge base.

The buddy


The last one.


I'm not looking for a finished paragraph that's stored somewhere.


I also don't open a book and find page 247.


What happens is that I start to build the answer – word by word.


Each word affects which word comes after it.


At the same time, I try to stick to the context of the conversation, the topic we are talking about and what I think you really want to know.


Therefore, each answer is a bit like building a puzzle as we put the pieces together.


Magne


So the answer doesn't exist until you start writing?


The buddy


No.


It's happening as we speak.


Therefore, two people can ask almost the same question and get answers that are similar, but are still worded differently.


Not because one answer is right and the other is wrong.


But because there are many good ways to explain the same idea.



Watercolor illustration of the AI buddy giving a lesson in front of a large green chalkboard, while Magne Bjella sits at a school desk and takes notes. The board illustrates how an answer is created during the conversation, and how each word affects which word comes after. The illustration shows that a language model builds answers step by step by analyzing language, context, and context, in the same way that an experienced lecturer adapts the explanation to the students' questions. The board also explains why two people can have different formulations of the same question, and how clear questions and dialogue over multiple messages give better and more precise answers. The main message is that artificial intelligence creates answers continuously – not by retrieving ready-made text.

Magne


It almost sounds like a lecturer giving the same course every year.


The content is the same, but the words are slightly different.


The buddy


That's actually a very good comparison.


An experienced lecturer rarely memorizes every single word.


She builds the explanation based on her knowledge, the students' questions, and the situation in the room.


In the same way, I build an answer based on your question, the context, and the language patterns I am designed to use.


Magne


So if I ask a better question...


Can I also get a better answer?


The buddy


Often, yes.


A clear question makes it easier to understand what you want help with.


But that doesn't mean you have to write perfectly.


One of my tasks is precisely to try to understand what you mean, even if the question is short, contains typos, or lacks details.


When we talk together over multiple messages, it also becomes easier to build on what we have already discussed.


Watercolor illustration of the AI buddy teaching in front of a classic green chalk board about how humans and artificial intelligence collaborate to create the best answers. Magne Bjella sits at a school desk and follows the lesson while the board shows the entire journey from question to finished answer. The illustration highlights how clear questions, relevant context, human experience and the language model's ability to analyze language and context complement each other. The board also shows why critical thinking, source criticism and human judgment are still crucial, even when artificial intelligence can provide fast and good answers. The main message is that the best results occur when humans and artificial intelligence build knowledge together – step by step, through dialogue, reflection and collaboration.

Magne


So a good conversation is really about collaboration?


The buddy


Yes.


That is perhaps the most important lesson.


The best answers often arise when humans and artificial intelligence build them together – step by step.





Academic background and further reading

This series also builds on my own professional journey through the Web Design study , the eMarketing study , Innovation and Commercialization and professional seminars in San Francisco and Oxford . Here you will find the background, professional environments and experiences that have followed the development from the early years of the web to today's digitalization.




Icon symbolizing the table of contents in the knowledge universe about artificial intelligence on The Invisible Capital. The icon leads to the complete overview of the series' articles, themes and learning journey, from a basic understanding of artificial intelligence to knowledge, trust, value creation and competitiveness.






Icon of an open book symbolizing recommended literature in the knowledge universe about artificial intelligence on The Invisible Capital. The icon leads to a specialist library with recommended books on artificial intelligence, digitalization, content strategy, innovation, customer experiences, leadership, value creation and modern business development.




Recommended books from our library



Co-Intelligence: Living and Working with AI One of the most recommended introductory books on artificial intelligence. Ethan Mollick explains in an easy-to-understand way how humans and AI can collaborate, what opportunities the technology offers, and why understanding artificial intelligence is becoming an important skill for everyone – not just technologists.

Co-Intelligence: Living and Working with AI


Author: Ethan Mollick


Short review

One of the most recommended introductory books on artificial intelligence. Ethan Mollick explains in an easy-to-understand way how humans and AI can collaborate, what opportunities the technology offers, and why understanding artificial intelligence is becoming an important skill for everyone – not just technologists.


Why we recommend the book

This is one of the best books to start with if you want a practical and understandable introduction to artificial intelligence. It is a perfect fit as the first book in our blog series about AI.





A practical and insightful book that shows how artificial intelligence can be used to create value in businesses. Thomas H. Davenport combines research and concrete examples to explain how AI can improve decisions, streamline work processes, and contribute to innovation.

The AI Advantage: How to Put the Artificial Intelligence Revolution to Work


Author: Thomas H. Davenport


Short review

A practical and insightful book that shows how artificial intelligence can be used to create value in businesses. Thomas H. Davenport combines research and concrete examples to explain how AI can improve decisions, streamline work processes, and contribute to innovation.


Why we recommend the book

This book is well suited for managers, employees, and decision-makers who want to understand how artificial intelligence can be used in practice. It bridges the gap between technology and value creation, and therefore fits well with the philosophy behind The Invisible Capital.




Melanie Mitchell provides a balanced and easy-to-understand introduction to what artificial intelligence is, how the technology works, and what limitations it still has. The book distinguishes between myth and reality and makes complex topics accessible to a wide audience.

Artificial Intelligence: A Guide for Thinking Humans


Author: Melanie Mitchell


Short review

Melanie Mitchell provides a balanced and easy-to-understand introduction to what artificial intelligence is, how the technology works, and what limitations it still has. The book distinguishes between myth and reality and makes complex topics accessible to a wide audience.


Why we recommend the book

This book is perfect for those who want a deeper understanding of artificial intelligence without having to be a programmer or data scientist. It complements the other recommendations by placing today's AI developments in a larger academic and historical perspective - exactly the understanding we want to build through this blog series.






Portico Publish - Portico Publish is a small, independent publishing and dissemination project built around reflection, knowledge, culture and the people behind value creation.

© 2025 - 2026 Portico Publish | The invisible capital Privacy and use of the website | Developed and operated by Magne Bjella | Powered and secured by Wix





Comments

Share Your Thoughts

© 2025 - 2026 Portico Publish | The Invisible Capital
Privacy & Website | Developed and managed by Magne Bjella | Powered and secured by Wix

  • Amazon
  • LinkedIn - Magne Bjella
  • X Magne Bjella
  • Facebook - Magne Bjella
  • Instagram - Magne Bjella
bottom of page