top of page

Part 31 - AI-Companion... how does artificial intelligence find, assess and use information?

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

When we ask an AI a question, it may seem like the answer comes immediately. But before an answer is written, a lot happens "behind the scenes". AI must interpret the question, consider what information is relevant, look for connections and build an answer based on probability and patterns. In this article, we take a closer look at how AI finds, evaluates and uses information – and why the quality of the information is crucial to the quality of the answer.


Large watercolor illustration of Magne and Kompisen walking through the historic Piazza del Campo in Siena, Italy, as they discuss how artificial intelligence finds, evaluates, and uses information. Surrounded by medieval architecture, cobblestone streets, the Palazzo Pubblico, and the iconic Torre del Mangia, the motif illustrates how knowledge is developed through dialogue, reflection, and curiosity. The main illustration visualizes the central theme of the article: how artificial intelligence first interprets questions, considers which information is most relevant, identifies patterns and connections, and then builds an answer based on language understanding and probability. The motif emphasizes that artificial intelligence does not function as a traditional reference book, but as an advanced system for analyzing language, context, and knowledge. The illustration is part of the Magne & Kompisen series on Den usynlige Kapitalen, where complex topics within artificial intelligence, digitalization, knowledge sharing, and value creation are explained through warm watercolors, educational dialogues, and human insight.

Magne & the Friend


Magne


Friend...

Now I'm beginning to understand that you don't think the way people do.


But I still wonder about one thing.


How do you actually find the information you use when answering?


The buddy

That's a good question.


Many people think I'm looking for one right answer.


That's not really how I work.


I will first try to understand the question.


I then consider which knowledge is most relevant.


Finally, I build an answer by putting together information that fits exactly what you're asking.


Magne

So...

You're not looking up a book?


The buddy


No.


I don't work like a reference book does.


I look for patterns.


Connected.


Concepts.


And how information is logically connected.


That is why the context surrounding the question is often as important as the question itself.


Magne


Does that mean you use all information equally?


The buddy


No.


Information has different quality.


Some are based on research.


Something is based on experience.


Something is well documented.


Anything else is uncertain or outright wrong.


Therefore, I always try to build answers that are as consistent and relevant as possible based on the information I have available.


Educational whiteboard watercolor from the article "How does artificial intelligence find, evaluate, and use information?" showing Magne and Kompisen in front of a green educational whiteboard with a view of Piazza del Campo and Torre del Mangia in Siena. The whiteboard introduces the first step in how artificial intelligence works: interpreting the question before attempting to answer. The illustration explains that artificial intelligence analyzes language, concepts, relationships, and context to understand what the user is really asking. Instead of looking up a one-size-fits-all answer, the system attempts to identify which themes, words, and relationships are most relevant. The warm watercolor style makes advanced AI principles easy to understand and shows how well-formulated questions and clear context lay the foundation for better answers. The illustration is part of the educational series Magne & Kompisen, where artificial intelligence is explained through dialogue, whiteboards, and visual models.

Magne

So...


So you evaluate information before using it?


Educational watercolor illustration of Magne and Kompisen in front of a green educational board with a view of Siena's famous cathedral and historic city environment. The board shows how artificial intelligence evaluates information through several steps before building an answer. Using illustrations, symbols and clear models, it explains how artificial intelligence evaluates relevance, quality, credibility, connections and patterns in available information. The illustration shows that artificial intelligence tries to find the most relevant information, compare different sources and build a logical understanding of the question. At the same time, it emphasizes that the quality of the answer always depends on the quality of the information the system is working with. The motif makes complex principles within artificial intelligence, information assessment and knowledge analysis easily understandable through warm watercolors and educational communication.

The buddy


Yes.


I am trying to find the information that best suits me.

the question.


But I could also be wrong.


If the information is incomplete, contradictory, or unclear, the answer may be less precise.


That's why good sources and clear questions are so important.


Magne

Then I begin to understand why we spend so much time on good content on our website.


Educational chalkboard watercolor showing Magne and Kompisen in front of a green chalkboard with a view of the impressive Siena Cathedral. The illustration visualizes how artificial intelligence builds an answer by combining relevant information, language understanding, context, logical connections and pattern recognition. Through simple illustrations, it explains how artificial intelligence first finds relevant information, then analyzes connections and finally builds an answer based on probability, language and context. The chalkboard emphasizes the central conclusion of the article: Good information creates better understanding – and better understanding gives better answers. The illustration is part of Magne & Kompisen, an educational illustration series on The Invisible Capital that makes advanced topics in artificial intelligence, digital communication, knowledge management and digital value creation accessible to both professionals and the general public.

The buddy

Exactly.


When a website is well structured, based on credible sources, and explains the topics thoroughly, it becomes easier for both humans and artificial intelligence to understand the content.


Good information creates better understanding.


And better understanding leads to better answers.


Academic specialization

Artificial intelligence doesn't work like a human

Explanation

Interpreting the question

AI analyzes language, concepts, and context before responding.

Assessing relevance

It attempts to find information that best fits the question.

Looking for patterns

AI builds answers by identifying connections in the information.

Building a response

The answer is put together based on probability, context and language understanding.

Depends on quality

Good sources and good content often provide better answers than inadequate information.





English technical term

Short explanation

Relevance

How well the information fits the question being asked.

Context

How information is interconnected and affects understanding.

Pattern

Repetitive structures that AI uses to interpret and build answers.

Information Quality

How reliable, up-to-date and relevant the information is.

Data Foundation

The information and material that underpins how a language model learns.

Knowledge Base

The sum of information and connections on which AI builds answers.

Relevance Assessment

The process of determining which information is most useful for a particular question.

Context

The information surrounding a question that helps AI understand the meaning.

Source


Where the information comes from.

Credibility

How reliable and trustworthy a source or information is.



We have just begun...

This is just one of many topics that are important to understand.

how artificial intelligence works. In the next articles, we will take a closer look at how AI assesses credibility, why good sources are crucial, how language models can be wrong, and how humans and artificial intelligence can collaborate to build knowledge.





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 subject 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



Book cover for Build a Large Language Model (From Scratch) by Sebastian Raschka – one of the most recommended books on how large language models are built and work. An inspiring book for anyone who wants to understand the technology behind ChatGPT, artificial intelligence and the digital solutions of the future. A natural choice for developers, managers, students and anyone who wants to delve into how language models learn and create value.

Build a Large Language Model (From Scratch)


Author: Sebastian Raschka


Short review

This book takes the reader behind the scenes and shows how a modern language model is actually built – step by step. Sebastian Raschka explains advanced concepts in an educational way and provides a unique understanding of how large language models like ChatGPT work. Although the book contains code examples, it is also very valuable for anyone who wants a deeper understanding of the technology behind artificial intelligence.


Why we recommend the book

One of the most talked about books on large language models. Perfect for those who want to understand how artificial intelligence works beneath the surface and why language models have become a revolution in digitalization and knowledge sharing.





Book cover for Quick Start Guide to Large Language Models by Sinan Ozdemir – a practical and inspiring book that explains how large language models like ChatGPT work and are used in modern businesses. A book we highly recommend to anyone who wants to understand artificial intelligence, language models and the digital working methods of the future.

Quick Start Guide to Large Language Models


Author: Janelle Shane


Short review

This book provides a practical and easy-to-understand introduction to large language models (LLMs). Sinan Ozdemir explains how language models are used in modern businesses, how they can be integrated into work processes, and why they have become one of the most important technologies in artificial intelligence.


Why we recommend the book

A very good book for anyone who wants a quick and practical introduction to language models. It is suitable for both beginners and professionals who want to understand how LLMs are used in practice.





Book cover for Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig – the world's most recognized textbook on artificial intelligence and a standard work at universities worldwide. A book that provides a thorough understanding of artificial intelligence, machine learning, language models and modern AI technology. An invaluable reference for anyone who wants to build solid knowledge about artificial intelligence and digitalization.

Artificial Intelligence: A Modern Approach: The Future Is Coming! Discover How Artificial Intelligence Will Change Your Life!


Authors: Stuart Russell & Peter Norvig


Short review

This is the world's most famous textbook on artificial intelligence and is used in universities worldwide. The book covers the entire subject area – from problem solving and machine learning to language understanding, robotics and ethics – and is considered a classic in the AI field.


Why we recommend the book

If you are only going to own one academic book on artificial intelligence, this is one of the very best choices. A timeless classic that provides a solid academic understanding of artificial intelligence and is still used as a syllabus at leading universities around the world.







Portico Publish - The publisher 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