50th Annual Summer Institute of Applied Statistics 2026

The featured speaker will be Julia Silge, Data Scientist and Software Engineer, Posit PBC

Large Language Models (LLMs) offer data scientists, statisticians, and other people who work with data unprecedented programmatic capabilities. The AI and LLM space is rife with jargon, but we can counteract this widespread obfuscation with a practical, grounded understanding of what common terms (“model provider”, “agent”, “tool call”, etc) mean, how components are combined to make an AI product, and how we can customize the behavior of these tools. This two-day workshop introduces ellmer (R) and chatlas (Python), open source packages that simplify LLM API integration, handling conversation complexities and enabling seamless interactions with AI models.

Participants will explore system prompt design, token management, and tool calling while building familiarity with current AI technologies. The workshop demonstrates that:

• Coding with LLMs unlocks possibilities beyond standard tools
• No advanced AI background is required
• Implementing AI can be both accessible and fruitful for people who work with data

Designed for AI newcomers and experienced data practitioners alike, the session covers LLM integration, Shiny web app development, and touches on advanced topics like Retrieval-Augmented Generation (RAG) and tool calling. Attendees will gain hands-on experience through guided exercises, learning how to build on top of these new technologies.

To view past presenters, click here.

To register, click here.

For questions regarding SIAS, contact Jill Stevenson at (801) 422-8067 or jstevenson@stat.byu.edu.