Explaining AI models and their outputs to non-technical stakeholders can be challenging due to their complexity or business expectations. This decreases the trust and adoption of models in production. This session will discuss a few practices that can help D&A professionals enhance explainability and trust in model predictions, facilitating responsible and ethical use of AI across various domains.

Although retrieval augmented generation is a very popular architectural pattern for delivering Q&A over complex internal information, it is also extremely hard to build a high quality, high accuracy RAG system. Come to this session to learn the 7 gotchas of RAG systems and best practices to improve their performance.