Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore how to build a conversational AI agent for data analysis using LangGraph in this 29-minute conference talk from EuroPython 2025. Learn about an innovative project at Merck KGaA's Life Science division that leverages LangGraph—a library for creating stateful, multi-actor applications with Large Language Models—to develop a self-served tool enabling interactive data querying, automatic code generation, and insights summarization. Discover the architecture of the LangGraph agentic framework and see how various tools integrate to process user queries, trigger analytical functions, and present data in user-friendly visual formats. Gain insights into evaluation methodologies using LangFuse and Ragas, with emphasis on metrics that ensure optimal performance and user satisfaction for LLM agent projects. Through real-world applications, understand how conversational agents can transform data interaction by making customized insights more accessible and intuitive, while learning practical strategies for evaluating AI-driven data analysis projects and exploring future advancements in this rapidly evolving field.
