- 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
1.9 Chapter summary
In this chapter, we have established the key principles of Generative Analysis, which is based first and foremost on communication. We presented a brief introduction to some important ideas from neuro linguistic programming (nlp) and General Semantics and introduced the concepts of distortion, deletion, and generalization that we will have much more to say about later. We also introduced a key metaphor: the map and the territory.
Generative Analysis is a process of abstraction—of capturing the pertinent details of the problem domain—and we spent quite a bit of time refining the notion of abstraction by considering the map of the London Underground.
An important part of the chapter was establishing the right level of abstraction for leveraging Generative AI, and we did this by generating Python code and UML models.
The final part of the chapter was a discussion of the Generative Analysis approach to modeling. We introduced the notions of software sanity, and the categories Interface Sane, Interface Un-sane, Implementation Sane, and Implementation Un-sane that give us a useful way to categorize software systems. We discussed the relationship of software sanity with Convergent Architecture, and then wrapped up the chapter with some practical advice about testing models.
