Databricks Foundational Workshops

Unity Gateway: Govern AI Costs, Access, and Interactions

New date coming soon

Effective governance is essential to democratizing data and AI in the age of LLMs and generative AI. Enterprises struggle with fragmented governance across databases, warehouses, lakes, and diverse data formats, which complicates discovery, access permissions, data usage, audits, and sharing. Additionally, users often cannot access the right data from their preferred tools, leading to vendor lock-in. Managing ML models and AI tools for regulatory compliance adds another layer of complexity.

Learn how Unity Gateway helps organisations lower AI costs without losing productivity. In this 90-minute hands-on workshop, you will configure and use a governed Model Service, add metadata for usage analysis, query cost and audit evidence, configure rate limits and budgets, manage Unity Catalog permissions, and test runtime service policies on model requests and responses. 

 
In this session, you will learn how to:

• - Configure a governed Model Service for AI workloads.
• - Assign Unity Catalog permissions to control model access.
• - Apply rate limits and budgets to manage AI costs.
• - Enforce guardrails and service policies on requests and responses.
• - Use observability and audit evidence to analyse usage, cost, and policy outcomes.

Building Modern Applications on Databricks with Lakebase

New date coming soon

Most application stacks are fragmented. Transactions live in one system, analytics in another, and pipelines try to stitch everything together.
That architecture slows development. Teams often spend more time debugging data movement than building features.

This workshop introduces a different approach. You will work with Lakebase, a fully managed Postgres database on Databricks that sits alongside the lakehouse, allowing your applications, analytics, and AI to operate on the same data.

The session demonstrates how modern application teams can move faster when apps, analytics, and AI run on the same data. You will work with Lakebase to spin up a database, connect with Python, run queries, and power real application workflows, showing how the lakehouse can support production-ready applications.

 
In this session, you will learn how to:

• - Run your application and analytics on the same data
• - Set up Lakebase on Databricks and start using it quickly
• - Connect your application using SQL, Python, and standard tools
• - Build features on live data instead of batch copies
• - Push lakehouse data directly into your application
• - Apply governance across both data and applications
• - Get closer to something you could run in production

Build, Orchestrate and Improve Multi-Agent Systems with Databricks

New date coming soon

Take a deep dive into building production-grade AI agent systems on Databricks. Using Agent Bricks, you'll construct a Knowledge Assistant grounded in real company data and extend it with an AI/BI Genie-powered structured data agent. Then orchestrate both into a multi-agent supervisor and iteratively improve response quality — all without writing a single line of code.

In 90 minutes, you'll walk away knowing how to combine unstructured and structured data, intelligently route queries across specialized agents and guide agent behavior using natural language feedback.
 

At this event, you will get the chance to:

• - Ground large language model (LLM) responses in living company knowledge bases and support ticket history using AI Search
• - Build a Knowledge Assistant agent using pre-built AI Search indices with no setup required
• - Query structured billing and customer data with Genie using plain natural language over SQL tables
• - Register Genie as an agent and plug it into a multi-agent workflow alongside your Knowledge Assistant
• - Orchestrate agents with a multi-agent supervisor that routes queries intelligently by data type

• - Improve response quality through natural language feedback
   

   

Who should attend

If you’re a data engineer, ML practitioner or technical architect who wants hands-on experience building multi-agent AI systems on the Databricks Data + AI Platform, this session is for you. No prior agent development experience required, and all lab environments are pre-configured.