Jason Lopatecki is CEO and Co-Founder of Arize AI.
In this keynote, he outlines a vision for LLM monitoring and LLM observability and covers everything from LLM traces and spans to LLM evals, prompt testing and iteration, RAG search and retrieval, and fine-tuning. He covers the wide array of LLM use cases — like chatbots, structured data extraction, summarization, Q&A assistants, web scraping, code generation, and tagging and labeling — before outlining supported LLM span types. He then previews an exciting launch around LLM evals.
This talk was originally delivered at “From Toy To Production: Building LLM-Powered Systems that Work in the Real World,” an event in New York City dedicated to scaling LLM-powered systems from experimental stages to real-world production environments.