AgentBricks vs Mosaic AI
Proposed session for SQLBits 2026TL; DR
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, and low‑code workflows, while Mosaic AI provides the broader infrastructure for model governance, routing, observability, and production‑grade agent systems. Attendees will learn when to use each, how they work together, and how to build scalable agentic applications across the Databricks platform.
Session Details
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, and low‑code workflows, while Mosaic AI provides the broader infrastructure for model governance, routing, observability, and production‑grade agent systems. Attendees will learn when to use each, how they work together, and how to build scalable agentic applications across the Databricks platform.
3 things you'll get out of this session
- Learn when to use AgentBricks
- Learn when to use Mosaic AI
- Learn how to build a platform with both in mind
Speakers
Gavita Regunath's previous sessions
Automated Machine Learning on Azure
AutoML which stands for Automated Machine Learning empowers data teams to quickly build and deploy machine learning models. It aims to reduce the time and expertise required to generate a machine learning model by automating the heavy lifting of preprocessing, feature engineering, model creation, tuning and evaluation.
When it comes to machine learning in Microsoft Azure, there are two main options for running your AutoML: (1) Azure Machine Learning Service and (2) Azure Databricks. This session will aim to introduce how to develop ML models using AutoML on both platforms, as well as the features of each and why you would choose one over the other.
How to get started with Computer Vision AutoML in Azure
In this talk, we will be leveraging Azure computer vision. The Azure Computer Vision is part of Azure Cognitive Services that provides pre-built, advanced algorithms that process and analyse images.
If you want to get started with computer vision but do not know where to start, then this talk will give you a good starting point to jumpstart your computer vision journey. You will leave this talk with an understanding of how to build and deploy your own computer vision models using Azure computer vision.
Keynote by The Community
Ben and Rob have found some wonderful folk to actually do the important parts of the community keynote. on the theme of
How to be a nonpassive member of the data community
AutoML: An Introduction To Get You Started
Understand how to get started with any machine learning project using Databricks AutoML
Tori Tompkins
toritompkins.co.uk/blog
Tori Tompkins's other proposed sessions for 2026
Unlocking the Potential of Retrieval-Augmented Generation (RAG) with Advanced Patterns - 2026
You Think Your MLOps Can Scale GenAI? Think Again. - 2026
No Code Agents with AgentBricks - 2026
Real-Time AI with Databricks Online Feature Stores: Powered by Lakebase - 2026