delivery

areasofinterest

track

type

level

industry

Sam Hashemi

“Make Me a Map”: Building a GIS Agent with Agent Bricks, MCP, and Lakebase

Circle K is activating customer data and loyalty insights via their CDP to deliver more relevant, personalized experiences across the customer journey. In this session, Jay Malepati, Global Director of Customer & Marketing Data Science at Circle K, will share how his team is building a stronger customer data foundation to better understand customer behavior, improve loyalty engagement, and automate personalization at scale. Attendees will learn how Circle K approaches customer intelligence, segmentation, and data-driven marketing in a complex, high-volume retail environment.

Global Director of Data Science

Jay Malepati

[CustomerLake] How Circle K Powers Personalized Loyalty Programs with Customer Data at Scale

As marketing teams look to deliver more tailored, measurable, and efficient customer experiences, a trusted Data Infrastructure is foundational to modern martech strategy. In this session, Luis Alonso, Head of Data Strategy & Engineering for Global Martech at HP, will share how HP is approaching customer data, identity, and analytics to support global marketing use cases across segmentation, activation, measurement, and AI. Attendees will learn what it takes to build a scalable customer data foundation that connects marketing ambition with governed, enterprise-ready data infrastructure.

Customer Data Strategy & Engineering 

luis alonso

[CustomerLake] How HP is building an AI-Ready, B2B GTM Data Infrastructure for Global Marketing

GM has leveraged their robust data foundations and modeling expertise to drive measurable marketing outcomes. Leveraging the Databricks platform and Acxiom product offerings, GM has built an intelligence layer across the customer lifecycle, applying identity resolution, propensity modeling, and audience optimization to power smarter, faster decisioning across channels.By operationalizing these capabilities at scale, GM is sharpening audience targeting, increasing marketing effectiveness, and accelerating time-to-activation across its brand portfolio. This session explores how GM and Acxiom are translating data infrastructure investments into real, quantifiable impact, and what it takes to make intelligence-driven marketing a repeatable, scalable practice.

Sr. Strategy Manager, Tech Enablement

Jennifer McCluskey

Automotive Client Partner

Jesse Henderson

SVP, Product Strategy & Ecosystem

Zachary Van Doren

[CustomerLake]Precision Targeting at Scale:How GM & Acxiom Are Turning Foundational Customer Intelligence into Measurable Outcomes

In early 2025, Alpura faced fragmented data, multiple BI tools, weak governance and no scalable AI foundation. In just 120 days, we rebuilt the entire data platform on Databricks. Using the Medallion Architecture (Bronze, Silver, Gold), Unity Catalog for enterprise governance and Databricks Metrics for a centralized semantic layer, we created a governed, scalable lakehouse foundation. We consolidated more than five legacy platforms without disrupting operations and eliminated KPI inconsistencies by standardizing business logic. On top of this foundation, we rapidly delivered 100+ AI/BI assets, including 10+ production-grade applications such as a Walmart Scintilla analytics app and an Ambassador Program app — built in days, not months. Leveraging Genie AI, we enabled conversational BI to accelerate adoption. This session shares a practical blueprint for building an AI/BI factory at enterprise speed.

Chief Data Officer

Javier Hauss

CTDO

Marvin Nahmias

0 to 100 AI/BI Apps in 120 Days: Building an Enterprise Data and AI Platform From Scratch @ Alpura

Industrial AI's real bottleneck isn't the model — it's the data foundation. Operational data has the classic 3 V's at extreme scale: Variety (hundreds of OEM protocols and naming conventions), Velocity (1-second sensor streams), and Volume — 3.2 billion events a day from a 10 GW renewable fleet.Nexalis is the cloud-native industrial data infrastructure layer for the AI era. A zero-copy architecture makes OT data available in your Databricks environment — cleansed, shaped, and AI-ready in under 4 seconds — unlocking the full analytics ladder: descriptive, diagnostic, predictive, and prescriptive.Three production deployments: EDF Power Solutions on Maverick6 (solar + battery); Clenera (1.6 GW today → 5+ GW); Calpine with Accure (predictive battery degradation deep inside the BESS).Same architecture, same pattern — heading next into conventional generation and nuclear. Anyone can dump events into a bucket. Cleansed, shaped, and AI-ready in less than 4 seconds is data engineering.

CEO & Co-Founder

Quentin Morel

10 Gigawatts of Renewables = 3.2 Billion Events a Day in the Databricks Lakehouse

Delta Lake and Iceberg excel at large-scale analytics, but they are not optimized for sub-second point lookups or full-text search. In operational workloads — such as security analytics, log investigation and telemetry — retrieval queries that require full scans or high-cardinality filtering can take minutes to hours, when seconds or milliseconds are required. I built IndexTables, an embedded, Tantivy-based indexing layer that runs directly inside Spark executors, enabling up to 1000× faster query performance while preserving the Lakehouse model. This session explores the architecture: object-storage-hosted indexes with ACID transactions, millisecond-latency aggregations over billions of rows, native time-series bucketing for efficient GROUP BY analytics and NVMe-backed caching with proactive pre-warming. Attendees will learn how Capital One is using IndexTables to complement Delta and Iceberg, creating lakehouse architectures that support both analytical and retrieval-heavy workloads.

VP, Distinguished Engineer

Scott Schenkein

1000× Faster Retrieval: Indexed and Full-Text Search in the Lakehouse

Ensemble Health Partners manages revenue cycle operations for 30+ health systems, processing 25 billion+ transactions across 800TB of healthcare financial data. Legacy SQL Server sprawl —1 5 individual databases with separate schemas —c reated silos that blocked cross-client insights and slowed AI innovation in an industry where providers operate on 1% margins. This session shows how Ensemble consolidated onto Databricks Lakebase as their AI-ready transactional layer, eliminating brittle pipelines and enabling self-service pods to materialize views directly from harmonized Delta tables. The results: 3–5% net revenue yield improvement ($30M+ per $1B health system), 20% organizational efficiency gain, and 10x reduction in failure rates — while powering agentic AI workflows for denial prevention, AR follow-up, and payer-behavior prediction at scale.

Grant Veazey

Field Engineering

Surya Sai Turaga

800TB, Zero Pipelines: How Ensemble Health Partners Built an AI-Ready Revenue Cycle on Lakebase

Great Southern Bank (GSB) has successfully migrated from SAS to Databricks - unlocking higher model accuracy, faster insights, and the ability to democratise data at scale using Genie and AI/BI. Importantly, GSB achieved this with a much smaller team than the major banks, demonstrating practical expertise and delivery experience that other organisations can learn from. To date, GSB has migrated and integrated 85% of its enterprise data onto the Databricks platform and is on track to shut down its legacy warehouse by 2026. Databricks AI capabilities are already delivering material value across traditional ML and gen AI use cases - e.g. a home-loan churn model was built by a single employee and matched the accuracy of a 3rd party model. On top of the enterprise data foundation, Genie Spaces now enable business users to self-serve insights faster and with improved accuracy. GSB is also accelerating value creation in areas such as complaints analysis and sentiment using GenAI.

Senior Solutions Architect

James McNiff

Head of Customer Technology Data and AI

Matt Cammack

A Different Way to Compete: How Great Southern Bank Went All In on Data and AI

The hardest part of real-time ML is the feature plumbing. Teams spend time creating and maintaining fragmented pipelines rather than focusing on their ML capabilities. Declarative Features breaks that cycle. Define what a feature is (source, entity, aggregation, time window) and let the platform compute it correctly in every context. This session covers Declarative Features, our managed feature pipeline offering, and explains how they can take your ML platform into the next phase of growth.

Software Engineer

Ian Ackerman

Sr. Product Manager

Nick Joung

A Simple, Managed Platform - Modern Feature Engineering on Databricks

Data exfiltration is one of the most serious security risks organizations face. It can expose sensitive information, leading to reputational damage and regulatory penalties. The challenge is that exfiltration can happen in many ways, including external attackers, poorly configured AI agents, insider mistakes, or malicious insiders, and is often hard to detect until the damage is done. In this lightning talk, we'll break down where exfiltration risks come from and what they may look like in Databricks (spoiler: it's not always a malicious actor!). We'll then introduce a framework for categorizing protection controls across three levels: data platform, compute, and storage. Using this framework, we'll discuss what risks to address today, tomorrow, and in the future with readily available controls at each level.  As we wrap-up our session, we'll give you a glimpse into implementing comprehensive egress monitoring: what's here now and what's coming. Walk away with a fresh perspective on data exfiltration risks and actions you can take today to secure and monitor your most sensitive workloads!

Staff Security Field Engineer

JD Braun

Product Manager

Robert Zhang

A Unified Approach to Data Exfiltration Protection and Egress Monitoring to Build Secure Agents

Delta Lake and Apache Iceberg™ have converged on similar ideas: columnar metadata for efficient pruning, manifest trees for scalability, and deletion vectors for fast updates. Yet today, we maintain two separate metadata structures, duplicating work and diverging in capabilities. The next major evolution of Delta Lake reimagines metadata from the ground up. This talk introduces a unified metadata architecture where Delta Lake commits store content metadata directly in Iceberg v4's adaptive metadata tree. Delta Lake gains efficient tree-structured manifests and Iceberg interoperability while preserving the transactional guarantees that Delta users depend on. Join us to see the future of lakehouse metadata.

Principal Software Engineer

Anoop Johnson

Micah Kornfield

A Unified Future for Delta and Apache Iceberg™

Business semantics is the missing bridge between raw data and real understanding for humans and AI alike. In this comprehensive session, the product team behind Unity Catalog’s business semantics takes you from A to Z: what business semantics is, why it matters and how an open and unified semantic layer transforms the way agents, apps and BI tools consume your data. We’ll start with the foundations, defining and governing business glossaries, tags, and semantic metadata within Unity Catalog. Then we’ll show what’s new: the latest capabilities that make semantics flow seamlessly across AI agents, applications and BI tools from a single governed source. See live demos of how unified semantics improve agent reasoning, enrich app experiences and build dashboard trust. Whether you’re just starting or scaling enterprise-wide, walk away with everything you need to make your data universally understood.

Director of Product Management

Can Efeoglu

Sr. Engineering Manager

Jasmeet Jaggi

A–Z of Unity Catalog Business Semantics: Open and Unified Semantics for Agents, Apps and BI

Workday needed to put trusted ML insights directly in the hands of sales, customer success and finance—fast. Before, delivering a single internal app required a bespoke full‑stack build and repeated reviews, stretching timelines to nearly a year. By shifting to Databricks Apps and building where the data already lives, Workday compressed delivery to weeks, launched three production AI applications in a single year, and scaled its flagship Sales Companion to 4,500+ active users. This session details the architecture and adoption playbook: Databricks Apps as the UI/middleware, MLflow‑powered components, retrieval‑augmented workflows for unstructured content, governed access with Unity Catalog and fast analytics via SQL Serverless—enabling conversational experiences that let business users self‑serve sentiment analysis, forecasting and KPI insights without waiting on the data science team or adding headcount.

Sr. Principal MLE

Tamilselvan Tamilmani

Director, GCO Technology & Architecture

Taylor Sewitt

Accelerating AI From Model to Impact at Workday With Databricks Apps

Onboarding a new data source at Corteva used to take 30–45 days. Now it’s 4–7 days, about 85% faster. The Lakeflow-first strategy and Unity Catalog helped standardize the ingestion‑to‑consumption pathway across 6 domains. Lakeflow Connect, Spark Declarative Pipelines and Jobs make pipeline runs repeatable and config‑driven. A lightweight metadata layer centralizes data cleansing, and an incremental DDL tool pushes schema changes safely through each environment. This pattern now underpins Corteva’s operational analytics. It accelerates root‑cause analysis linking field variability to dryer‑bin stabilization, improves throughput across 35 seed sites, and strengthens seed quality. Today, the setup covers 5,000+ tables from 15+ sources, shortening time‑to‑insight and speeding partner onboarding. Attendees will leave with a reusable Lakeflow‑first ingestion pattern, a metadata‑driven data quality blueprint and a safe schema‑evolution workflow across environments.

Sr. Forward Deployed Engineer

Harshit Rai

Data and AI Platform Engineer

Mehul Bhuva

Accelerating Corteva’s Data Source Onboarding With Lakeflow

Accenture's Framework for Agents turns AI development from a bespoke project into a repeatable product motion. It gives teams a reusable foundational layer that standardizes ingestion, retrieval, evaluation, guardrails, and cost governance, allowing developers to compose vertical solutions instead of rebuilding plumbing.The framework is 100% Databricks native: Lakebase for agent state, Databricks Apps for user surfaces, Unity Catalog for governed data access, and AI Gateway for model routing and policy enforcement. Every deployment is tuned against business outcomes.Healthcare is the first industry solution built on this framework, targeting a major pain point: patients spending 15 to 20 minutes on hold to understand coverage. Accenture's Healthcare agent cuts this wait to just 5 minutes, answering complex eligibility questions in real time with 93 to 95% grounded accuracy. In this session, Accenture shares a concrete blueprint for turning industry agents into a repeatable platform.

Managing Director, Accenture Data & AI

Prakash Trivedi

Accelerating Industry Solutions Leveraging the Power of Agents on Databricks

This presentation shows how Nationwide modernized its ServiceNow platform, transforming it from a highly customized, rigid system into a modern, scalable ITSM and data platform by leveraging Lakeflow Connect’s native capabilities to efficiently ingest, store, and curate data for current and future analytics needs. Previously, legacy data was extracted via APIs into Oracle and scattered across siloed stores, creating governance gaps, slow refresh cycles, and poor data quality. By adopting a Lakehouse foundation with incremental and CDC pipelines, Nationwide now benefits from unified governance, clear data lineage, simplified security, and faster time to value. The reimplementation also simplifies integrations, accelerates reporting, and reduces technical debt, all while preserving historical insight.

Product Architect

Ramki Lakshminarayan

Accelerating ITSM Modernization with Lakeflow Connect: Nationwide’s Platform Upgrade

Our team started on Geospatial journey with Databricks DBR 16.X, from legacy project migration and continued to expand by ingesting and processing three different geospatial datasets (HD USHR maps, public OSM and curated OSM (Overture)). We applied different optimization techniques to make spatial joins more performant and worked closely with Databricks Geospatial team in testing out incremental improvements in DBR, culminating in large scale performance increase on DBR 17.X bringing support to geospatial data types (GEOMETRY, GEOGRAPHY) as dedicated data types that could be stored in delta table. A significant optimization was observed in spatial joins, which could eliminate previously used optimization techniques, making data pipelines maintenance easier. All of these improvements enabled us to enrich internal datasets based on various road attributes from these datasets and use them in analytics, training and potential reinforcement learning applications where needed.

Lead Software Engineer, Data

Chinmay Gupte

Senior Data Engineer, Autonomy

Filip Ilic

Staff Product Manager

Kent Marten

Accelerating Rivian's Autonomy Flywheel: Geospatial Intelligence at Scale

Closing the books every month is still slow and manual for many finance teams. In this session, we will walk through a monthly financial closing for a mid‑size retailer and show how we tackle two of the most painful steps with Databricks One: reconciling gaps between CRM invoices and accounting numbers and running variance analysis to explain differences between actual results and budget. We will follow a finance controller using an AI/BI dashboard to spot issues, Genie in natural language to investigate root causes and draft variance commentary and a Databricks app to apply the corrections safely, update the numbers and generate the final reporting deck.Attendees will see how business users can make financial closing faster, simplify investigations and produce more reliable reports with less manual effort — all from a single, unified workspace.

Solutions Architect

Christophe Chieu

Francis Laurens

Accelerating the Monthly Financial Closing With Genie

After migrating from Snowflake, Addepar ventured deep into Databricks' native AI/BI suite. This talk shares our practitioner's roadmap for accelerating "speed to value" by building analytics directly where data lives. We explore why we chose AI/BI over external tools and how we serve as early adopters pushing the platform's limits.Key takeaways:- The AI-Assisted Analyst: Leveraging Databricks Assistant to chat through notebook discovery, bypass syntax struggles, and cure "analyst's block" with AI-suggested Dashboard visuals.- Metadata as Code: Why rich Unity Catalog metadata is the critical UI for accurate GenAI.- Metric Views > Tables: Defining semantics once for both Dashboards and Genie to ensure consistent answers, rather than relying on static tables or views.- Genie & Agents: Tips for "teaching" Genie spaces and early experiments using Agent Bricks to orchestrate structured analytics alongside unstructured knowledge agents.

Manager, Data Analytics

Chris Krysinski

Accelerating the Speed to Value of Analytics with Databricks AI/BI & Agents

Investment professionals currently spend 12 hours weekly on manual fund screening, leading to operational inefficiencies and lost alpha opportunities. LSEG is leveraging Databricks to orchestrate Genie Spaces across the Lipper fund dataset of 350,000+ investments.Our solution enables users to perform complex fund screening using natural language. By employing a multi-agent supervisor to coordinate specialized Genie Spaces—such as Fund Universe, Performance & Risk, and Flows—users can execute queries like “UK equity funds with 3-year annualized return > 8% and AUM > 500m” against Lipper APIs and tables.This architecture streamlines the workflow sequence from report generation to portfolio optimization, allowing portfolio managers and analysts to identify investment strategies in minutes rather than hours. By leveraging Databricks Multi Agent Supervisor and LSEG’s trusted AI-ready data, firms can significantly reduce operational costs and improve decision-making efficiency.

Director of Product

Adam Towne

Activating Alpha Generation With Multi Agent AI for Fund Screening

Agents are becoming first-class users of the data stack, but they inherit 1990s-era connectivity: slow row-oriented APIs, heavy SDKs, and brittle system-specific connectors. For AI-driven workflows making fast tool calls across systems, this isn’t just slow—it’s terrible agent ergonomics, leading to failures, retries, and need for human intervention. This talk explains why ADBC (Arrow Database Connectivity) is emerging as the universal connector for agentic data workflows: a vendor-neutral API and driver standard that ships Arrow columnar results, enabling fast data access across languages and engines. We’ll show why this matters for agents: frequent queries, tight latency/cost budgets, and the need for safe, reliable access to the tabular truth. You’ll leave with a clear model for where ADBC fits in lakehouse architectures, why it aligns with Databricks and open standards, and a how to move from framework-heavy integrations to lean, CLI-first building blocks guided by agent skills.

Co-Founder and CEO

Ian Cook

ADBC and the Future of Universal Data Connectivity for Agentic Systems

MATCH_RECOGNIZE is landing on Databricks SQL — and it changes how analysts express row patterns. This session is demo-driven, built around production-grade examples — the kind of pattern queries that already run in pipelines, dashboards, and alerts. For each one we watch the query shrink from dozens of lines to a few. Readable. Maintainable. A fraction of the cost to run. You'll leave able to write — and challenge — patterns the way you'd say them out loud.

Sr. Specialist Solutions Architect DWH

Fabien Contaminard

Serge Rielau

Advanced SQL Patterns for Production Analytics

Agents have arrived. Evaluation workflows need to catch up.The bottleneck is knowing what to evaluate. You can’t catch failures you don’t know exist, and in production agents, they’re subtle: unclear tool definitions, bloated context, brittle handoffs, and inefficiencies that compound across long sessions. Manual trace review is the only way to discover them, but it doesn’t scale. Blind spots accumulate.Agent as a Judge closes this gap. Where LLM-as-a-judge scores predefined criteria, evaluation agents do open-ended discovery. They work directly on raw traces, surface recurring failure modes, and turn those findings into targeted, high-signal evaluators — a step toward agents that improve agents.We’ll show how this works in Phoenix’s open-source evaluation agent, running on Phoenix’s own production traces. You’ll see what it surfaced, how it compares to human reviewers, and what it takes to trust agents with the work of evaluating agents.

Senior AI Engineer

Elizabeth Hutton

Agent as a Judge: Scaling AI Evaluation for the Agentic Era

This hands-on course introduces learners to evaluating, governing, and securing agentic AI systems on Databricks. You'll begin by exploring the motivation for evaluation and governance frameworks and how they connect to the Databricks Data Intelligence Platform. Next, you'll learn how to apply MLflow evaluation metrics and a variety of evaluation techniques, including online evaluation, synthetic evaluation, and building evaluation datasets from MLflow traces. The course then examines how Unity Catalog governance extends to agents' functions, models, and tools, ensuring proper access control, auditability, and compliance. Finally, you'll learn Databricks AI Security Framework (DASF) and how to secure agents with Mosaic AI Gateway, applying guardrails, rate limits, and policy filters to enforce safe and reliable usage.Note: Hands-on training courses will be updated to reflect the newest product and feature announcements from Data + AI Summit in June 2026. Prerequisites<ul>	<li style="list-style-type: disc;">Familiarity with the Databricks Data Intelligence Platform, including Unity Catalog for governance and model management</li>	<li style="list-style-type: disc;">Intermediate Python programming experience</li>	<li style="list-style-type: disc;">Familiarity with Generative AI fundamentals, including RAG architectures and their components (chunking, embeddings, vector stores)</li>	<li style="list-style-type: disc;">Basic knowledge of MLflow for experiment tracking and model lifecycle management</li>	<li style="list-style-type: disc;">General awareness of data governance principles, including access control, data lineage, and data privacy</li></ul>

Senior Technical Curriculum Developer

Matthew McCoy

Agent Evaluations

The journey from traditional machine learning models to AI systems demands a new, specialized set of operational practices. This talk traces the evolution of core DevOps principles from the decade of MLOps to the Agents era, where we must plan for deploying and maintaining autonomous, multi-step AI agents that can reason, plan, and take actions in the real world using external tools.The talk will show how classic DevOps tenets like continuous deployment must be radically re-engineered to tackle core AgentOps challenges. Authors of The Databricks Big Book of Agent Ops will cover:Ensuring Maturity of Operational Controls: How critical operational controls must evolve to support multi-agent architectures.Distributed Tracing and Observability: Transforming single-step I/O logs into traces essential for debugging and explaining agent behavior.Governed Deployment and Rollback: Establishing AgentOps CI/CD pipelines that treat configurations (prompts, tools, routing logic) as code

Staff AI Forward-deployed Engineer

Jeanne Choo

 AI Solutions Architect

Kyra Wulffert

Agent Ops on Databricks, Powered by Omnigent

When your data consumers shift from 10,000 humans to 100,000 high-speed agents, “governance” can no longer mean a wiki page or a PDF policy document. Agents don’t read wikis; they need semantic, machine-readable guardrails. In this talk, the Data Platform team discusses our pivot to “agent-ready governance.” We are moving beyond simple access control lists (ACLs) to a model where Unity Catalog provides deep semantic context, usage constraints and “rules of the road” that our 100,000 agents can natively understand. Join us to see how we ensure that our digital workforce operates safely, preventing the chaos of 100,000 bots making bad decisions at machine speed.

Sr. Staff Software Engineer 

Amit Pahwa

Senior Software Engineer

Prashant Gupta

Agent Ready Data Governance: Databricks on Databricks

If we are building a future with 100,000 agents accessing our platform, relying on human administrators to click buttons and approve tickets is a non-starter. The math simply doesn’t work; human admin teams cannot scale linearly with an exponential agent workforce. This session explores how the Data Platform team is solving this by building “agentic admins” — autonomous systems capable of managing the platform for us. We will discuss the shift from manual provisioning to agent-led resource management, permissions granting and configuration tuning. Learn how we are architecting the control plane that allows a small team of humans to govern an army of 100,000 digital users without burning out.

Staff Software Engineer

James Burns

Agentic Admins: Managing Databricks @ Databricks

Agents promise to scale instant access to data insights across organizations. However, most data warehouses were built for humans reading dashboards. Agents expose every assumption that breaks. Flawed semantics lead to hallucination, fragmented governance exposes improper data access, and cost/performance issues explode when one analyst becomes a thousand agents. In this session we'll walk through what agentic analytics looks like in practice on Databricks Lakehouse, demoing the patterns customers are running in production today. Following these patterns, you can dramatically increase your data team's impact across your organization while reducing time-to-insight. You'll leave with a clear model of approaches to agentic analytics at scale, and see why Databricks Lakehouse is built for it.

Associate Product Manager

Ben Tripp

Adoption Lead, AI + DBSQL

Moe Steller

Agentic Analytics on Databricks Lakehouse

Genie Code is an autonomous AI partner for data work, with depth across the data engineering lifecycle. We show how builders use it to iterate on Spark Declarative Pipelines and Lakeflow Jobs, accelerating authoring. It knows your data, grounded in Unity Catalog metadata, semantics, and governance policies. This grounding helps Genie Code take accurate and context-aware actions. Beyond authoring, Genie Code keeps workflows healthy, proactively monitoring and maintaining data and AI in production. We discuss how it autonomously detects, diagnoses, and proposes fixes the moment failures happen, with every agent running sandboxed, so production stays untouched.

Sr. Staff Product Manager

Gal Oshri

Principal Engineer

Lennart Kats

Agentic Data Engineering with Genie Code and Genie ZeroOps

Genie Code adds tremendous value for data engineers - unifying and automating much of the ingest, ETL and streaming process. Hear from Bilal Aslam (Senior Director of Product Management) and our customer SEGA on how to use Genie Code for agentic data engineering, automating much of the process of building intelligent data pipelines. It integrates into the broader Databricks environment, and with Lakeflow and Spark Declarative Pipelines is a fully governed way to prepare and analyze data directly in Databricks.

Staff Tech Marketing Engineer

Amber Roberts

Data Developer

Anastasiya Lavrenchuk

Sr. Director of Product Management

Bilal Aslam

Chief AI Officer - EMEA

Maria Zervou

Agentic Data Engineering: Automating Pipelines with Genie Code

Global Head of Evangelism

Ari Kaplan

Agentic Data Foundation

McAfee protects millions of users through products like Scam Detector and Social Privacy Manager. Iteration on adaptive pricing models was bottlenecked by slow, manual feature engineering. To unlock value from massive user signals, we needed to move from ideation to production fast. In this talk, we show how we built an autonomous feature engineering agent on Agent Bricks that cuts engineering cycles by 60% — replacing manual SQL with an agent that reasons, iterates, and converges. This is the next step in a journey where AI-assisted feature store and personalization have contributed to $54M+ in incremental revenue over three years. The agentic approach is how we make that capability reproducible, faster, and accessible without a team of ML specialists. Attendees will see a live blueprint of our agentic pipeline:<ul>	<li>Analyze & ideate: Agent loads domain context and playbook from Unity Catalog, analyzes baseline and proposes features via LLM reasoning</li>	<li>Generate & evaluate: Agent writes code, executes in sandbox, evaluates against baseline and logs every iteration to MLflow.</li>	<li>Converge & deploy: Best features publish directly to Unity Catalog feature store.</li></ul> Walk away with a reproducible blueprint for agentic feature engineering on Databricks.

Senior Applied Science Manager

Arul Bharathi

Agentic Feature Engineering: How McAfee Drives Personalization With Agent Bricks

De-identifying clinical data is essential for research and secondary use, yet current approaches are costly and require constant manual tuning as data distributions change. This session introduces an agentic approach to automating privacy-preserving pipelines on the Databricks Lakehouse.We present an Agentic De-Identification Framework that treats the pipeline itself as an autonomous agent, minimizing human effort while maximizing security and compliance.Attendees will learn how to use Agent Bricks to fit de-identification models and entity resolution logic to customer data; apply agentic de-identification across structured data, clinical notes, and imaging metadata using Mosaic AI Agent framework; and register core de-identification logic as governed Unity Catalog Functions.We conclude by showing how AgentOps is operationalized with MLflow tracing, Unity Catalog governance, and Mosaic AI Gateway Guardrails to deliver auditable, secure PHI protection at scale.

David Talby

Veysel Kocaman

Agentic PHI De-Identification Across Multimodal Healthcare Data on Databricks

AI-driven attacks now operate at machine scale, with mean time to exploit collapsing from 23 days to just under 2 days. SIEMs as we know them today are going to disappear because this new agentic era you are dealing with unprecedented threats. That’s why Databricks announced Lakewatch, the Open Agentic SIEM. Instead of locking security data into proprietary systems with per-byte ingest licensing, Lakewatch lets teams store all their security telemetry in open formats, retain it for years, and run agentic AI across it. Security teams gain complete visibility across the enterprise and can deploy defensive security agents to automate threat detection and response at massive scale.

GM of Lakewatch

Andrew Krioukov

Head of BuiltOn Field Engineering

Jason Pohl

Agentic Security: Real-Time Threat Detection with Lakewatch

Industrial enterprises sit on decades of unstructured knowledge locked in engineering drawings, work orders, and maintenance logs. Join this session to see how leading manufacturers, energy producers, and transportation operators are using multi-agent supervisor architectures on Databricks to extract, validate, and reason over complex technical documents - cutting review cycles, improving compliance, and turning institutional knowledge into a competitive edge.

Sr. Solutions Architect

David Rogers

Global Leader -  AI Innovation & Arch

Karthik Josyula

Global Procurement Excellence Leader

Shakeel Ahmed

Senior Supply Chain Systems Manager

mitchell Calvert

Agents and AI track:
Multi-Agent AI for the Industrial Supply Chain

Maintenance technicians at 7-Eleven rely on preventive maintenance, catalogue and parts documents for equipment like HVACs and ovens — often using only their phones. These documents span thousands of files in formats like PDFs and spreadsheets stored in shared drives, making it hard to find the right information quickly. High attrition and missed training sessions compounds knowledge gaps. To address this, 7-Eleven developed a GenAI agentic system using Mosaic AI, Agent Bricks and Databricks Hybrid Search that enables technicians to 1) Retrieve relevant maintenance documents with concise answers 2) Capture equipment images and receive troubleshooting solutions 3) Access parts information by equipment brand 4) Get solutions from the internet. This chatbot bridges knowledge gaps with instant access to institutional knowledge. We will walk through how we built this system, our evaluation methodologies and the three-step prompt framework including guardrails for safe internet searches.

Staff Engineer - Manager

Sumedh Datar

AI Agents for the Frontline: 7-Eleven’s GenAI Maintenance Assistant

PREVIEW THE SESSIONS

SESSIONS