Generative Analysis for Generative AI
- 1.1 Introduction
- 1.2 Chapter contents
- 1.3 Communication and neuro linguistic programming (nlp)
- 1.4 Abstraction
- 1.5 Finding the right level of abstraction for Generative AI
- 1.6 Choice of Generative AI
- 1.7 Applying Generative AI to an example problem domain
- 1.8 Modeling in Generative Analysis
- 1.9 Chapter summary
This chapter is from the book
This chapter is from the book
This chapter is from the book
1.1 Introduction
In this chapter, you will learn about three key principles of Generative Analysis: communication, modeling, and abstraction.
Generative Analysis begins with communication, so we will introduce some key ideas now and spend a lot of time on the details later in the book. We will also discuss our approach to modeling, using the metaphor of a map and its territory. We will show how this relates to abstraction.
Abstraction is the fundamental process that drives Generative Analysis and software engineering in general. We will explain levels of abstraction and demonstrate that to successfully use Generative AI in software engineering, we need to operate at a very specific level of abstraction, one that we have already used very successfully in our previous book, Enterprise Patterns and MDA [Arlow 2].
The conversations with the Microsoft and Google Generative AIs all occurred in 2023 when Copilot, the Microsoft Generative AI, was called Bing, and Gemini, the Google Generative AI, was called Bard. In this text, we use the new names, Copilot and Gemini.
