Summary In this episode of the Data Engineering Podcast Arun Joseph talks about developing and implementing agent platforms to empower businesses with agentic capabilities. From leading AI engineering at Deutsche Telekom to his current entrepreneurial venture focused on multi-agent systems, Arun shares insights on building agentic systems at an organizational scale, highlighting the importance of robust models, data connectivity, and orchestration loops. Listen in as he discusses the challenges of managing data context and cost in large-scale agent systems, the need for a unified context management platform to prevent data silos, and the potential for open-source projects like LMOS to provide a foundational substrate for agentic use cases that can transform enterprise architectures by enabling more efficient data management and decision-making processes.

Announcements Hello and welcome to the Data Engineering Podcast, the show about modern data managementData migrations are brutal. They drag on for months—sometimes years—burning through resources and crushing team morale. Datafold's AI-powered Migration Agent changes all that. Their unique combination of AI code translation and automated data validation has helped companies complete migrations up to 10 times faster than manual approaches. And they're so confident in their solution, they'll actually guarantee your timeline in writing. Ready to turn your year-long migration into weeks? Visit dataengineeringpodcast.com/datafold today for the details. This episode is brought to you by Coresignal, your go-to source for high-quality public web data to power best-in-class AI products. Instead of spending time collecting, cleaning, and enriching data in-house, use ready-made multi-source B2B data that can be smoothly integrated into your systems via APIs or as datasets. With over 3 billion data records from 15+ online sources, Coresignal delivers high-quality data on companies, employees, and jobs. It is powering decision-making for more than 700 companies across AI, investment, HR tech, sales tech, and market intelligence industries. A founding member of the Ethical Web Data Collection Initiative, Coresignal stands out not only for its data quality but also for its commitment to responsible data collection practices. Recognized as the top data provider by Datarade for two consecutive years, Coresignal is the go-to partner for those who need fresh, accurate, and ethically sourced B2B data at scale. Discover how Coresignal's data can enhance your AI platforms. Visit dataengineeringpodcast.com/coresignal to start your free 14-day trial. Your host is Tobias Macey and today I'm interviewing Arun Joseph about building an agent platform to empower the business to adopt agentic capabilitiesInterview IntroductionHow did you get involved in the area of data management?Can you start by giving an overview of how Deutsche Telekom has been approaching applications of generative AI?What are the key challenges that have slowed adoption/implementation?Enabling non-engineering teams to define and manage AI agents in production is a challenging goal. From a data engineering perspective, what does the abstraction layer for these teams look like? How do you manage the underlying data pipelines, versioning of agents, and monitoring of these user-defined agents?What was your process for developing the architecture and interfaces for what ultimately became the LMOS?How do the principles of operatings systems help with managing the abstractions and composability of the framework?Can you describe the overall architecture of the LMOS?What does a typical workflow look like for someone who wants to build a new agent use case?How do you handle data discovery and embedding generation to avoid unnecessary duplication of processing?With your focus on openness and local control, how do you see your work complementing projects like OumiWhat are the most interesting, innovative, or unexpected ways that you have seen LMOS used?What are the most interesting, unexpected, or challenging lessons that you have learned while working on LMOS?When is LMOS the wrong choice?What do you have planned for the future of LMOS and MASAIC?Contact Info LinkedInParting Question From your perspective, what is the biggest gap in the tooling or technology for data management today?Closing Announcements Thank you for listening! Don't forget to check out our other shows. Podcast.init covers the Python language, its community, and the innovative ways it is being used. The AI Engineering Podcast is your guide to the fast-moving world of building AI systems.Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes.If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.Links LMOSDeutsche TelekomMASAICOpenAI Agents SDKRAG == Retrieval Augmented GenerationLangChainMarvin MinskyVector DatabaseMCP == Model Context ProtocolA2A (Agent to Agent) ProtocolQdrantLlamaIndexDVC == Data Version ControlKubernetesKotlinIstioXerox PARC)OODA (Observe, Orient, Decide, Act) LoopThe intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA

Summary In this episode of the Data Engineering Podcast we welcome back Nick Schrock, CTO and founder of Dagster Labs, to discuss the evolving landscape of data engineering in the age of AI. As AI begins to impact data platforms and the role of data engineers, Nick shares his insights on how it will ultimately enhance productivity and expand software engineering's scope. He delves into the current state of AI adoption, the importance of maintaining core data engineering principles, and the need for human oversight when leveraging AI tools effectively. Nick also introduces Dagster's new components feature, designed to modularize and standardize data transformation processes, making it easier for teams to collaborate and integrate AI into their workflows. Join in to explore the future of data engineering, the potential for AI to abstract away complexity, and the importance of open standards in preventing walled gardens in the tech industry.

Announcements Hello and welcome to the Data Engineering Podcast, the show about modern data managementThis episode is brought to you by Coresignal, your go-to source for high-quality public web data to power best-in-class AI products. Instead of spending time collecting, cleaning, and enriching data in-house, use ready-made multi-source B2B data that can be smoothly integrated into your systems via APIs or as datasets. With over 3 billion data records from 15+ online sources, Coresignal delivers high-quality data on companies, employees, and jobs. It is powering decision-making for more than 700 companies across AI, investment, HR tech, sales tech, and market intelligence industries. A founding member of the Ethical Web Data Collection Initiative, Coresignal stands out not only for its data quality but also for its commitment to responsible data collection practices. Recognized as the top data provider by Datarade for two consecutive years, Coresignal is the go-to partner for those who need fresh, accurate, and ethically sourced B2B data at scale. Discover how Coresignal's data can enhance your AI platforms. Visit dataengineeringpodcast.com/coresignal to start your free 14-day trial. Data migrations are brutal. They drag on for months—sometimes years—burning through resources and crushing team morale. Datafold's AI-powered Migration Agent changes all that. Their unique combination of AI code translation and automated data validation has helped companies complete migrations up to 10 times faster than manual approaches. And they're so confident in their solution, they'll actually guarantee your timeline in writing. Ready to turn your year-long migration into weeks? Visit dataengineeringpodcast.com/datafold today for the details. This is a pharmaceutical Ad for Soda Data Quality. Do you suffer from chronic dashboard distrust? Are broken pipelines and silent schema changes wreaking havoc on your analytics? You may be experiencing symptoms of Undiagnosed Data Quality Syndrome — also known as UDQS. Ask your data team about Soda. With Soda Metrics Observability, you can track the health of your KPIs and metrics across the business — automatically detecting anomalies before your CEO does. It’s 70% more accurate than industry benchmarks, and the fastest in the category, analyzing 1.1 billion rows in just 64 seconds. And with Collaborative Data Contracts, engineers and business can finally agree on what “done” looks like — so you can stop fighting over column names, and start trusting your data again.Whether you’re a data engineer, analytics lead, or just someone who cries when a dashboard flatlines, Soda may be right for you. Side effects of implementing Soda may include: Increased trust in your metrics, reduced late-night Slack emergencies, spontaneous high-fives across departments, fewer meetings and less back-and-forth with business stakeholders, and in rare cases, a newfound love of data. Sign up today to get a chance to win a $1000+ custom mechanical keyboard. Visit dataengineeringpodcast.com/soda to sign up and follow Soda’s launch week. It starts June 9th.Your host is Tobias Macey and today I'm interviewing Nick Schrock about lowering the barrier to entry for data platform consumersInterview IntroductionHow did you get involved in the area of data management?Can you start by giving your summary of the impact that the tidal wave of AI has had on data platforms and data teams?For anyone who hasn't heard of Dagster, can you give a quick summary of the project?What are the notable changes in the Dagster project in the past year?What are the ecosystem pressures that have shaped the ways that you think about the features and trajectory of Dagster as a project/product/community?In your recent release you introduced "components", which is a substantial change in how you enable teams to collaborate on data problems. What was the motivating factor in that work and how does it change the ways that organizations engage with their data?tension between being flexible and extensible vs. opinionated and constrainedincreased dependency on orchestration with LLM use casesreducing the barrier to contribution for data platform/pipelinesbringing application engineers into the mixchallenges of meeting users/teams where they are (languages, platform investments, etc.)What are the most interesting, innovative, or unexpected ways that you have seen teams applying the Components pattern?What are the most interesting, unexpected, or challenging lessons that you have learned while working on the latest iterations of Dagster?When is Dagster the wrong choice?What do you have planned for the future of Dagster?Contact Info LinkedInParting Question From your perspective, what is the biggest gap in the tooling or technology for data management today?Links Dagster+ EpisodeDagster Components Slide DeckThe Rise Of Medium CodeLakehouse ArchitectureIcebergDagster ComponentsPydantic ModelsKubernetesDagster PipesRuby on RailsdbtSlingFivetranTemporalMCP == Model Context ProtocolThe intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA

Explore advanced governance and authentication patterns for building secure, enterprise-grade apps with Databricks Apps. Learn how to configure complex permissions and manage access control using Unity Catalog. We’ll dive into “on-behalf-of-user” authentication — allowing agents to enforce user-specific access controls — and cover API-based authentication, including PATs and OAuth flows for external integrations. We’ll also highlight how Addepar uses these capabilities to securely build and scale applications that handle sensitive financial data. Whether you're building internal tools or customer-facing apps, this session will equip you with the patterns and tools to ensure robust, secure access in your Databricks apps.

Taxonomy generation is a challenge across industries such as retail, manufacturing and e-commerce. Incomplete or inconsistent taxonomies can lead to fragmented data insights, missed monetization opportunities and stalled revenue growth. In this session, we will explore a modern approach to solving this problem by leveraging Databricks platform to build a scalable compound AI architecture for automated taxonomy generation. The first half of the session will walk you through the business significance and implications of taxonomy, followed by a technical deep dive in building an architecture for taxonomy implementation on the Databricks platform using a compound AI architecture. We will walk attendees through the anatomy of taxonomy generation, showcasing an innovative solution that combines multimodal and text-based LLMs, internal data sources and external API calls. This ensemble approach ensures more accurate, comprehensive and adaptable taxonomies that align with business needs.

This session explains how we've made our Apache Spark™ versionless for end users by introducing a stable client API, environment versioning and automatic remediation. These capabilities have enabled auto-upgrade of hundreds of millions of workloads with minimal disruption for Serverless Notebooks and Jobs. We'll also introduce a new approach to dependency management using environments. Admins will learn how to speed up package installation with Default Base Environments, and users will see how to manage custom environments for their own workloads.

In enterprise AI, Evaluation-Driven Development (EDD) ensures reliable, efficient systems by embedding continuous assessment and improvement into the AI development lifecycle. High-quality evaluation datasets are created using techniques like document analysis, synthetic data generation via Mosaic AI’s synthetic data generation API, SME validation, and relevance filtering, reducing manual effort and accelerating workflows. EDD focuses on metrics such as context relevance, groundedness, and response accuracy to identify and address issues like retrieval errors or model limitations. Custom LLM judges, tailored to domain-specific needs like PII detection or tone assessment, enhance evaluations. By leveraging tools like Mosaic AI Agent Framework and Agent Evaluation, MLflow, EDD automates data tracking, streamlines workflows, and quantifies improvements, transforming AI development for delivering scalable, high-performing systems that drive measurable organizational value.

DigiCert is a digital security company that provides digital certificates, encryption and authentication services and serves 88% of the Fortune 500, securing over 28 billion web connections daily. Our project aggregates and analyzes certificate transparency logs via public APIs to provide comprehensive market and competitive intelligence. Instead of relying on third-party providers with limited data, our project gives full control, deeper insights and automation. Databricks has helped us reliably poll public APIs in a scalable manner that fetches millions of events daily, deduplicate and store them in our Delta tables. We specifically use Spark for parallel processing, structured streaming for real-time ingestion and deduplication, Delta tables for data reliability, pools and jobs to ensure our costs are optimized. These technologies help us keep our data fresh, accurate and cost effective. This data has helped our sales team with real-time intelligence, ensuring DigiCert's success.

While Databricks powers your data lakehouse, DataHub delivers the critical context layer connecting your entire ecosystem. We'll demonstrate how DataHub extends Unity Catalog to provide comprehensive metadata intelligence across platforms. DataHub's real-time platform:Cut AI model time-to-market with our unified REST and GraphQL APIs that ensure models train on reliable and compliant data from across platforms, with complete lineage trackingDecrease data incidents by 60% using our event-driven architecture that instantly propagates changes across systems*Transform data discovery from days to minutes with AI-powered search and natural language interfaces.Leaders use DataHub to transform Databricks data into integrated insights that drive business value. See our demo of syncback technology—detecting sensitive data and enforcing Databricks access controls automatically—plus our AI assistant that enhances' LLMs with cross-platform metadata.

In this session, we’ll introduce Zerobus Direct Write API, part of Lakeflow Connect, which enables you to push data directly to your lakehouse and simplify ingestion for IOT, clickstreams, telemetry, and more. We’ll start with an overview of the ingestion landscape to date. Then, we'll cover how you can “shift left” with Zerobus, embedding data ingestion into your operational systems to make analytics and AI a core component of the business, rather than an afterthought. The result is a significantly simpler architecture that scales your operations, using this new paradigm to skip unnecessary hops. We'll also highlight one of our early customers, Joby Aviation and how they use Zerobus. Finally, we’ll provide a framework to help you understand when to use Zerobus versus other ingestion offerings—and we’ll wrap up with a live Q&A so that you can hit the ground running with your own use cases.

Join this session for a concise tour of Apache Spark™ 4.0’s most notable enhancements: SQL features: ANSI by default, scripting, SQL pipe syntax, SQL UDF, session variable, view schema evolution, etc. Data type: VARIANT type, string collation Python features: Python data source, plotting API, etc. Streaming improvements: State store data source, state store checkpoint v2, arbitrary state v2, etc. Spark Connect improvements: More API coverage, thin client, unified Scala interface, etc. Infrastructure: Better error message, structured logging, new Java/Scala version support, etc. Whether you’re a seasoned Spark user or new to the ecosystem, this talk will prepare you to leverage Spark 4.0’s latest innovations for modern data and AI pipelines.

Redox & Databricks direct integration can streamline your interoperability workflows from responding in record time to preauthorization requests to letting attending physicians know about a change in risk for sepsis and readmission in near real time from ADTs. Data engineers will learn how to create fully-streaming ETL pipelines for ingesting, parsing and acting on insights from Redox FHIR bundles delivered directly to Unity Catalog volumes. Once available in the Lakehouse, AI/BI Dashboards and Agentic Frameworks help write FHIR messages back to Redox for direct push down to EMR systems. Parsing FHIR bundle resources has never been easier with SQL combined with the new VARIANT data type in Delta and streaming table creation against Serverless DBSQL Warehouses. We'll also use Databricks accelerators dbignite and redoxwrite for writing and posting FHIR bundles back to Redox integrated EMRs and we'll extend AI/BI with Unity Catalog SQL UDFs and the Redox API for use in Genie.

This presentation will review the new change feed and snapshot capabilities in Apache Spark™ Structured Streaming’s State Reader API. The State Reader API enables users to access and analyze Structured Streaming's internal state data. Readers will learn how to leverage the new features to debug, troubleshoot and analyze state changes efficiently, making streaming workloads easier to manage at scale.

PepsiCo, given its scale, has numerous teams leveraging different tools and engines to access data and perform analytics and AI. To streamline governance across this diverse ecosystem, PepsiCo unifies its data and AI assets under an open and enterprise-grade governance framework with Unity Catalog. In this session, we'll explore real-world examples of how PepsiCo extends Unity Catalog’s governance to all its data and AI assets, enabling secure collaboration even for teams outside Databricks. Learn how PepsiCo architects permissions using service principals and service accounts to authenticate with Unity Catalog, building a multi-engine architecture with seamless and open governance. Attendees will gain practical insights into designing a scalable, flexible data platform that unifies governance across all teams while embracing openness and interoperability.

Modern data science teams face the challenge of navigating complex landscapes of languages, tools and infrastructure. Positron, Posit’s next-generation IDE, offers a powerful environment tailored for data science, seamlessly integrating with Databricks to empower teams working in Python and R. Now integrated within Posit Workbench, Positron enables data scientists to efficiently develop, iterate and analyze data with Databricks — all while maintaining their preferred workflows. In this session, we’ll explore how Python and R users can develop, deploy and scale their data science workflows by combining Posit tools with Databricks. We’ll showcase how Positron simplifies development for both Python and R and how Posit Connect enables seamless deployment of applications, reports and APIs powered by Databricks. Join us to see how Posit + Databricks create a frictionless, scalable and collaborative data science experience — so your teams can focus on insights, not infrastructure.

American Airlines migrated from Hive Metastore to Unity Catalog using automated processes with Databricks APIs and GitHub Actions. This automation streamlined the migration for many applications within AA, ensuring consistency, efficiency and minimal disruption while enhancing data governance and disaster recovery capabilities.

Want to create AI agents that can do more than just generate text? Join us to explore how combining Databricks' Mosaic AI Agent Framework with the Model Context Protocol (MCP) unlocks powerful tool-calling capabilities. We'll show you how MCP provides a standardized way for AI agents to interact with external tools, data and APIs, solving the headache of fragmented integration approaches. Learn to build agents that can retrieve both structured and unstructured data, execute custom code and tackle real enterprise challenges. Key takeaways: Implementing MCP-enabled tool-calling in your AI agents Prototyping in AI Playground and exporting for deployment Integrating Unity Catalog functions as agent tools Ensuring governance and security for enterprise deployments Whether you're building customer service bots or data analysis assistants, you'll leave with practical know-how to create powerful, governed AI agents.

The lakehouse is built for storage flexibility, but what about compute? In this session, we’ll explore how Unity Catalog enables you to connect and govern multiple compute engines across your data ecosystem. With open APIs and support for the Iceberg REST Catalog, UC lets you extend access to engines like Trino, DuckDB, and Flink while maintaining centralized security, lineage, and interoperability. We will show how you can get started today working with engines like Apache Spark and Starburst to read and write to UC managed tables with some exciting demos. Learn how to bring flexibility to your compute layer—without compromising control.

Intuit leverages Databricks Clean Rooms to create a secure, privacy-safe lending marketplace, enabling small business lending partners to perform analytics and deploy ML/AI workflows on sensitive data assets. This session explores the technical foundations of building isolated clean rooms across multiple partners and cloud providers, differentiating Databricks Clean Rooms from market alternatives. We'll demonstrate our automated approach to clean room lifecycle management using APIs, covering creation, collaborator onboarding, data asset sharing, workflow orchestration and activity auditing. The integration with Unity Catalog for managing clean room inputs and outputs will also be discussed. Attendees will gain insights into harnessing collaborative ML/AI potential, support various languages and workloads, and enable complex computations without compromising sensitive information in Clean Rooms.

Join us for an interactive Ask Me Anything (AMA) session on the latest advancements in Apache Spark 4, including Spark Connect — the new client-server architecture enabling seamless integration with IDEs, notebooks and custom applications. Learn about performance improvements, enhanced APIs and best practices for leveraging Spark’s next-generation features. Whether you're a data engineer, Spark developer or big data enthusiast, bring your questions on architecture, real-world use cases and how these innovations can optimize your workflows. Don’t miss this chance to dive deep into the future of distributed computing with Spark!