Tori Tompkins

Databricks now offers two paths for building enterprise AI agents: AgentBricks and Mosaic AI. Join Tori and Gavi, 2 AI MVPs as they compare these capabilities, architecture, and ideal use cases. We’ll explore how AgentBricks simplifies agent creation with automated evaluation, synthetic data,...

AgentBricks is a new framework for designing, testing, and deploying production-grade AI agents natively on the Databricks Lakehouse. This session introduces the architecture behind AgentBricks and shows how it enables teams to create reliable, auditable, and enterprise-ready agents. We’ll...

Retrieval-Augmented Generation (RAG) is revolutionizing the capabilities of Generative AI by addressing critical limitations such as knowledge cut-offs, hallucinations, and lack of domain specificity. By integrating external knowledge sources with LLMs, RAG ensures outputs are more accurate, dynamic, and contextually relevant than ever before. In this session, we’ll begin with why RAG is essential for building scalable, trustworthy AI systems and before diving into advanced patterns like Modular RAG for adaptable designs, Graph RAG for structured data handling, and Voice RAG for audio-driven retrieval. Additionally, we’ll explore Corrective RAG, Branched RAG, and RAG-Fusion to tackle complex, multi-modal challenges. Whether you’re new to RAG or looking to refine your approach, this session will equip you with the tools and strategies to harness the full power of RAG workflows.

Evaluating LLMs is essential for ensuring they perform accurately and align with safety standards. This talk explores two frameworks for LLM Evaluation: RAGAS and MLFlow. We’ll explore practical applications of these frameworks, including a live demo that walks through setting up an evaluation...

In the fast-growing world of data, there's no one-size-fits-all skill set for data professionals. Join us as we define roles, explore essential skillsets, and share our personal journeys, revealing how these roles collaborate in daily operations and shape typical data projects.

Deploying machine learning models still remains one of data science's largest challenge, but MLOps is your answer. We'll explore how Databricks can be an end-to-end MLOps tool and the one-stop solution to this problem. Session includes practical demos on: Mlflow, Feature Store, Real-Time Serving...

Arguably the largest challenge in ML today is effectively deploying reliable and efficient models into production, with experts quoting that as many as 90% of model created never make it to production. MLOps streamlines the process of taking machine learning models to production, and then maintaining and monitoring them. With new MLOps micro-venders popping up every day, is there a tool that does everything? In this session, we will consider Databricks as an end-to-end MLOps tool, exploring collaborative workspaces, feature stores, model registries and model serving. We will also touch upon other critical MLOps practices such as model fairness, explainability and monitoring. Including practical demos of Databricks Feature Store, MLFlow and real-time Model Serving, this session is suitable for Data Scientists and Machine Learning Engineers of all levels.

Over time, machine learning models will degrade for a number of reasons. Maybe you have a book recommendation model but your customers preferences are changing, or maybe your customers behaviour has changed since the Covid-19 Lockdown. In this talk, I will cover the 4 types of model decay and the steps you can take to detect and mitigate against them.

In this session, we will cut through the marketing buzzwords to share experiences, tips, and tricks on how to be successful with Data Science and Analytics in the real world. Tune in to hear the team share real-world experience and get takeaways from industry insiders on real projects with...