Building with Generative AI: The Tricks and Tips You Need to Avoid Pitfalls

Title of talk: Building with Generative AI: The Tricks and Tips You Need to Avoid Common Pitfalls, by Ian Massingham

Abstract:
In this talk, you will learn about some of the common challenges that you might encounter while developing meaningful applications with generative AI models. Using non-deterministic systems as the basis for important applications is certainly an ‘interesting’ new frontier for software development, but hope is not lost. In this session, we will explore some of the well known (and less well known) issues in building applications on the APIs provided by Generative AI providers, and on ‘open’ models, such as Mistral, Llama, or DeepSeek. We will also (of course) dive into some of the approaches that you can take to address these challenges, including agent/MCP integration and graph-based memory, mitigating some of the inherent behaviors within Generative AI models, and enabling you to build more reliable and robust systems on top of Generative models, unlocking the potential of this new development paradigm.

Professional Bio:

Ian Massingham is a seasoned technology executive with extensive experience in cloud computing, data technology, startups, and developer relations. He is currently with Griptape, an early stage startup focusing on agentic AI and LLM application development. Prior to 2021, Ian spent nearly eight years at AWS, joining the company in December 2013, before AWS had gained significant enterprise adoption in Europe. During his tenure at AWS, Ian held various roles in Developer Relations and Evangelism, starting in this function and moving into a worldwide leadership position as Global Director, Worldwide Solutions Architecture for Startups.