Summary The purpose of business intelligence systems is to allow anyone in the business to access and decode data to help them make informed decisions. Unfortunately this often turns into an exercise in frustration for everyone involved due to complex workflows and hard-to-understand dashboards. The team at Zenlytic have leaned on the promise of large language models to build an AI agent that lets you converse with your data. In this episode they share their journey through the fast-moving landscape of generative AI and unpack the difference between an AI chatbot and an AI agent. Announcements Hello and welcome to the Data Engineering Podcast, the show about modern data management This episode is supported by Code Comments, an original podcast from Red Hat. As someone who listens to the Data Engineering Podcast, you know that the road from tool selection to production readiness is anything but smooth or straight. In Code Comments, host Jamie Parker, Red Hatter and experienced engineer, shares the journey of technologists from across the industry and their hard-won lessons in implementing new technologies. I listened to the recent episode "Transforming Your Database" and appreciated the valuable advice on how to approach the selection and integration of new databases in applications and the impact on team dynamics. There are 3 seasons of great episodes and new ones landing everywhere you listen to podcasts. Search for "Code Commentst" in your podcast player or go to dataengineeringpodcast.com/codecomments today to subscribe. My thanks to the team at Code Comments for their support. Data lakes are notoriously complex. For data engineers who battle to build and scale high quality data workflows on the data lake, Starburst is an end-to-end data lakehouse platform built on Trino, the query engine Apache Iceberg was designed for, with complete support for all table formats including Apache Iceberg, Hive, and Delta Lake. Trusted by teams of all sizes, including Comcast and Doordash. Want to see Starburst in action? Go to dataengineeringpodcast.com/starburst and get $500 in credits to try Starburst Galaxy today, the easiest and fastest way to get started using Trino. Your host is Tobias Macey and today I'm interviewing Ryan Janssen and Paul Blankley about their experiences building AI powered agents for interacting with your data Interview Introduction How did you get involved in data? In AI? Can you describe what Zenlytic is and the role that AI is playing in your platform? What have been the key stages in your AI journey? What are some of the dead ends that you ran into along the path to where you are today? What are some of the persistent challenges that you are facing? So tell us more about data agents. Firstly, what are data agents and why do you think they're important? How are data agents different from chatbots? Are data agents harder to build? How do you make them work in production? What other technical architectures have you had to develop to support the use of AI in Zenlytic? How have you approached the work of customer education as you introduce this functionality? What are some of the most interesting or erroneous misconceptions that you have heard about what the AI can and can't do? How have you balanced accuracy/trustworthiness with user experience and flexibility in the conversational AI, given the potential for these models to create erroneous responses? What are the most interesting, innovative, or unexpected ways that you have seen your AI agent used? What are the most interesting, unexpected, or challenging lessons that you have learned while working on building an AI agent for business intelligence? When is an AI agent the wrong choice? What do you have planned for the future of AI in the Zenlytic product? Contact Info Ryan LinkedIn Paul LinkedIn Parting Question From your perspective, what is the biggest gap in the tooling or technology for data management today? Closing Annou