Using AI in Software Design: How ChatGPT Can Help With Creating a Solution Architecture
Conference (ADVANCED level)
Room 8
Artificial intelligence, or AI, is becoming a big part of our lives. One type of AI is Large Language Models (LLMs), like chatGPT. This talk will show how chatGPT can help with complex tasks in software design, such as the tasks in the iSAQB Advanced Exam.
We will delve into the intricacies of conversing with chatGPT, illustrating the strategies needed to generate productive prompts and effectively utilize the model as a sparring partner. The talk will exemplify these concepts by taking the audience on a step-by-step journey through the process of tackling the iSAQB Advanced Example Exam, utilizing chatGPT.
We will demonstrate how to prepare for a chat session with chatGPT, how to generate robust prompts, and how to manage the chat for optimal outcomes. We aim to highlight the model’s capabilities as an interactive tool that can provide valuable insights and streamline the process of developing software architecture.
Whether you are a seasoned architect or a novice in the field, this presentation will equip you with novel techniques to navigate the challenging landscape of software architecture with the assistance of AI.
Ralf D. Müller
DB Systel GmbH
Ralf has continuously improved his skills in over 25 years in the software industry and has evolved from a software developer to an experienced software architect. In addition to designing software architectures, he attaches great importance to the clear communication and documentation of his ideas. With this goal in mind, Ralf started the open source project docToolchain, which deals with the effective documentation of software architectures. He is also responsible for creating the various formats of the arc42 template. As a CPSA-Advanced certified software architect, Ralf shares his knowledge and experience in trainings and talks to show others how to keep architecture documentation simple and up-to-date.
During the last few month, which are years in the world of AI, he did a deep dive into the realms of prompt engineering.