Colton Peltier

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.

Databricks Model Serving supports deployments ranging from classical ML models on custom-CPU workloads to foundation models with dedicated provisioned throughput endpoints. But what about the use-cases that need any of the 1000s of other open-source or fine-tuned LLMs? Deploying them efficiently can be challenging. This breakout session explores deploying LLMs on custom-GPU endpoints with vLLM. In it, we’ll examine: - Serverless GPU Compute: How it simplifies the deployment process, saving hours on configuration work alone. - vLLM + GPU workloads: How they work in tandem on the platform to deliver high-throughput inference with scalable infrastructure. - Implementation: A step-by-step code walkthrough for packaging models, configuring vLLM runtime, and deployment! Serving LLMs on GPUs doesn’t have to be scary. Learn more about how Databricks enables you to deploy even your most demanding model serving workloads!

We present AT&T AutoClassify, built jointly between AT&T's Chief Data Office (CDO) and Databricks professional services, a novel end-to-end system for automatic multi-head binary classifications from unlabeled text data. Our approach automates the challenge of creating labeled datasets and training multi-head binary classifiers with minimal human intervention. Starting only from a corpus of unlabeled text and a list of desired labels, AT&T AutoClassify leverages advanced natural language processing techniques to automatically mine relevant examples from raw text, fine-tune embedding models and train individual classifier heads for multiple true/false labels. This solution can reduce LLM classification costs by 1,000x, making it an efficient solution in operational costs. The end result is a highly optimized and low-cost model servable in Databricks capable of taking raw text and producing multiple binary classifications. An example use case using call transcripts will be examined.

Enterprises generate massive amounts of unstructured data — from support tickets and PDFs to emails and product images. But extracting insight from that data requires brittle pipelines and complex tools. Databricks AI Functions make this simpler. In this session, you’ll learn how to apply powerful language and vision models directly within your SQL and ETL workflows — no endpoints, no infrastructure, no rewrites. We’ll explore practical use cases and best practices for analyzing complex documents, classifying issues, translating content, and inspecting images — all in a way that’s scalable, declarative, and secure. What you’ll learn: - How to run state-of-the-art LLMs like GPT-4, Claude Sonnet 4, and Llama 4 on your data - How to build scalable, multimodal ETL workflows for text and images - Best practices for prompts, cost, and error handling in production - Real-world examples of GenAI use cases powered by AI Functions