Platform engineering in the age of LLMs

Businesses have started leveraging large language models (LLMs) to add intelligence to their apps. While developers are pivoting to prompt engineering, what does it mean for platform teams? Is it still business as usual?

ChatGPT heralds another "iPhone" or "cloud" moment in the world of applications. Massive investments are being made in anticipation of a Cambrian explosion of AI-enabled apps, autonomous agents, and multimedia creativity. Just like the cloud shook the way we built and deployed apps, this new modality will change the nature and skills needed for platform engineers. Through the lens of a real-world AI application, we will explore the emerging challenges accompanying the integration of LLMs, from scalability and security to governance and ethical considerations. Simultaneously, we reiterate the enduring principles that remain the bedrock of effective platform engineering.

This session is designed for platform engineers, architects, and leaders navigating the complexities of incorporating AI into their ecosystems. Attendees will leave with a nuanced understanding of how to adapt their strategies, processes, and mindsets to thrive in the age of LLMs, ensuring their platforms are robust, adaptable, and forward-thinking.