Modernizing Systems Observability with AI and LLMs with Jason Hand

Organizations of all kinds face similar challenges with managing the vast amounts of data their systems generate, and traditional monitoring methods often struggle to effectively handle the increasing complexity and scale. In this session, we’ll take a close look at how AI and Large Language Models (LLMs) are redefining observability by automating data analysis, detecting anomalies instantly, enabling more intuitive system interactions, and assisting in post-incident learning opportunities.
Through real-world examples, we’ll learn how AI-driven observability uncovers hidden patterns, minimizes false alarms, and accelerates correlation discovery, leading to faster and more accurate issue resolution and enhanced understanding of how our systems work.
Join me in a breakdown of how today’s AI-powered monitoring is enhancing system reliability and reducing the need for manual troubleshooting, all while improving overall performance and bringing systems into the modern world of observability.

1 - Generative AI and LLMs now allow for streamlined observability by automating data analysis and instantly detecting anomalies, making system monitoring more efficient.
2 - Generative AI and LLMs now identify hidden patterns in complex data, reduce false alarms, and accelerate issue correlation and resolution.
3 - Generative AI and LLMs powered monitoring now improves system reliability by reducing manual troubleshooting, enhancing overall performance, and modernizing observability practices.

Senior Developer Advocate at Datadog, focused on DevOps, SRE, and AI. Committed to empowering developers with modern engineering techniques for scalable, reliable, and explainable systems.