Luis Moros

Pre-sales Solution Architects (SAs) lose momentum navigating enterprise information silos. At Databricks, hyper-growth GTM and a fast-changing product stack amplify the problem. We built an Agentic Research Assistant that turns internal GTM knowledge into a conversational solution-design engine aligned to real pre-sales workflows.This session is a technical deep dive into the pipeline: a streaming event-driven architecture integrated with Databricks Model Serving, MLflow, and Lakehouse-native state management for real-time adaptability and observability.Highlights Workflow-to-tool modeling for field-aligned agent actions Lakehouse state store for conversation memory + tool-call trajectories Intent-aware retrieval with Instructed Retrievers Conversational reasoning using a DSPy ReAct extension Continuous optimization with DSPy + GEPA from historical trajectoriesA blueprint to move beyond basic RAG to self-improving agents that accelerate technical discovery and solutioning.

As companies increasingly adopt Generative AI, they're faced with a new challenge: managing multiple AI assistants. What if you could have a single, intuitive interface that automatically directs questions to the best assistant for the task? Join us to discover how to implement a flexible Routing Agent that streamlines working with multiple AI Assistants. We'll show you how to leverage Databricks and DSPy 3.0 to simplify adding this powerful pattern to your system. We'll dive into the essential aspects including: - Using DSPy optimizers to maximize correct route selections - Optimizing smaller models to reduce latency - Creating stateful interactions - Designing for growth and adaptability to support tens or hundreds of AI Assistants - Ensuring authorized access to AI Assistants - Tracking performance in production environments We'll share real-world examples that you can apply today. You'll leave with the knowledge to make your AI system run smoothly and efficiently.