From Context to Semantics: How Metadata Powers Agentic AI
Summary
In this episode Suresh Srinivas and Sriharsha Chintalapani explore how metadata platforms are evolving from human-centric catalogs into the foundational context layer for AI and agentic systems. They discuss the origins and growth of OpenMetadata and Collate, why “context” is necessary but “semantics” is critical for precise AI outcomes, and how a schema-first, API-first, unified platform enables discovery, observability, and governance in one workflow. They share how AI agents can now automate documentation, classification, data quality testing, and enforcement of policies, and why aligning governance with user identity and intent is essential as agentic access scales. They also dig into scalability strategies, MCP-based agent workflows, AI governance (including model/agent tracking), and the emerging convergence of big data with ontologies to deliver machine-understandable meaning.
Announcements
Hello and welcome to the Data Engineering Podcast, the show about modern data management
Data teams everywhere face the same problem: they're forcing ML models, streaming data, and real-time processing through orchestration tools built for simple ETL. The result? Inflexible infrastructure that can't adapt to different workloads. That's why Cash App and Cisco rely on Prefect. Cash App's fraud detection team got what they needed - flexible compute options, isolated environments for custom packages, and seamless data exchange between workflows. Each model runs on the right infrastructure, whether that's high-memory machines or distributed compute. Orchestration is the foundation that determines whether your data team ships or struggles. ETL, ML model training, AI Engineering, Streaming - Prefect runs it all from ingestion to activation in one platform. Whoop and 1Password also trust Prefect for their data operations. If these industry leaders use Prefect for critical workflows, see what it can do for you at dataengineeringpodcast.com/prefect.
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.
Composable data infrastructure is great, until you spend all of your time gluing it together. Bruin is an open source framework, driven from the command line, that makes integration a breeze. Write Python and SQL to handle the business logic, and let Bruin handle the heavy lifting of data movement, lineage tracking, data quality monitoring, and governance enforcement. Bruin allows you to build end-to-end data workflows using AI, has connectors for hundreds of platforms, and helps data teams deliver faster. Teams that use Bruin need less engineering effort to process data and benefit from a fully integrated data platform. Go to dataengineeringpodcast.com/bruin today to get started. And for dbt Cloud customers, they'll give you $1,000 credit to migrate to Bruin Cloud.
You’re a developer who wants to innovate—instead, you’re stuck fixing bottlenecks and fighting legacy code. MongoDB can help. It’s a flexible, unified platform that’s built for developers, by developers. MongoDB is ACID compliant, Enterprise-ready, with the capabilities you need to ship AI apps—fast. That’s why so many of the Fortune 500 trust MongoDB with their most critical workloads. Ready to think outside rows and columns? Start building at MongoDB.com/Build
Your host is Tobias Macey and today I'm interviewing Suresh Srinivas and Sriharsha Chintalapani about how metadata catalogs provide the context clues necessary to give meaning to your data for AI systems
Interview
Introduction
How did you get involved in the area of data management?
Can you start by giving an overview of the roles that metadata catalogs are playing in the current state of the ecosystem?
How has the OpenMetadata platform evolved over the past 4 years?How has the focus on LLMs/generative AI changed the trajectory of services like OpenMetadata?
The initial set of use cases for data catalogs was to facilitate discovery and documentation of data assets for human consumption. What are the structural elements of that effort that have paid dividends for an AI audience?How does the AI audience change the requirements around the cataloging and presentation of metadata?
One of the constant challenges in data infrastructure now is the tension of making data accessible to AI systems (agentic or otherwise) and incorporating AI into the inner loop of the service. What are the opportunities for bringing AI inside the boundaries of a system like OpenMetadata vs. as a client or consumer of the platform?
The key phrase of the past ~2 years is "context engineering". What role does the metadata catalog play in that undertaking?What are the capabilities that the catalog needs to be able to effectively populate and curate that context?
How much awareness does the LLM or agent need to have to be able to use the catalog effectively?
What does a typical workflow/agent loop look like when it is using something like OpenMetadata in pursuit of knowledge that it needs to achieve an objective?
How do agentic use cases strain the existing set of governance frameworks?What new considerations (procedural or technical) need to be factored into governance practices to balance velocity with security?
What are the most interesting, innovative, or unexpected ways that you have seen OpenMetadata/Collate used in AI/agentic contexts?
What are the most interesting, unexpected, or challenging lessons that you have learned while working on OpenMetadata/Collate?
When is OpenMetadata/Collate the wrong choice?
What do you have planned for the future of OpenMetadata?
Contact Info
SureshLinkedIn
SriharshaLinkedIn
Parting Question
From your perspective, what is the biggest gap in the tooling or technology for data management today?
Links
OpenMetadata Podcast Episode
Hadoop
Hortonworks
Context Engineering
MCP == Model Context Protocol
JSON Schema
dbt
LangSmith
OpenMetadata MCP Server
API Gateway
The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA
Eliminate Friction In Your Data Platform Through Unified Metadata Using OpenMetadata
Summary
A significant source of friction and wasted effort in building and integrating data management systems is the fragmentation of metadata across various tools. After experiencing the impacts of fragmented metadata and previous attempts at building a solution Suresh Srinivas and Sriharsha Chintalapani created the OpenMetadata project. In this episode they share the lessons that they have learned through their previous attempts and the positive impact that a unified metadata layer had during their time at Uber. They also explain how the OpenMetadat project is aiming to be a common standard for defining and storing metadata for every use case in data platforms and the ways that they are architecting the reference implementation to simplify its adoption. This is an ambitious and exciting project, so listen and try it out today.
Announcements
Hello and welcome to the Data Engineering Podcast, the show about modern data management
When you’re ready to build your next pipeline, or want to test out the projects you hear about on the show, you’ll need somewhere to deploy it, so check out our friends at Linode. With their managed Kubernetes platform it’s now even easier to deploy and scale your workflows, or try out the latest Helm charts from tools like Pulsar and Pachyderm. With simple pricing, fast networking, object storage, and worldwide data centers, you’ve got everything you need to run a bulletproof data platform. Go to dataengineeringpodcast.com/linode today and get a $100 credit to try out a Kubernetes cluster of your own. And don’t forget to thank them for their continued support of this show!
Struggling with broken pipelines? Stale dashboards? Missing data? If this resonates with you, you’re not alone. Data engineers struggling with unreliable data need look no further than Monte Carlo, the world’s first end-to-end, fully automated Data Observability Platform! In the same way that application performance monitoring ensures reliable software and keeps application downtime at bay, Monte Carlo solves the costly problem of broken data pipelines. Monte Carlo monitors and alerts for data issues across your data warehouses, data lakes, ETL, and business intelligence, reducing time to detection and resolution from weeks or days to just minutes. Start trusting your data with Monte Carlo today! Visit dataengineeringpodcast.com/impact today to save your spot at IMPACT: The Data Observability Summit a half-day virtual event featuring the first U.S. Chief Data Scientist, founder of the Data Mesh, Creator of Apache Airflow, and more data pioneers spearheading some of the biggest movements in data. The first 50 to RSVP with this link will be entered to win an Oculus Quest 2 — Advanced All-In-One Virtual Reality Headset. RSVP today – you don’t want to miss it!
Are you bored with writing scripts to move data into SaaS tools like Salesforce, Marketo, or Facebook Ads? Hightouch is the easiest way to sync data into the platforms that your business teams rely on. The data you’re looking for is already in your data warehouse and BI tools. Connect your warehouse to Hightouch, paste a SQL query, and use their visual mapper to specify how data should appear in your SaaS systems. No more scripts, just SQL. Supercharge your business teams with customer data using Hightouch for Reverse ETL today. Get started for free at dataengineeringpodcast.com/hightouch.
Your host is Tobias Macey and today I’m interviewing Sriharsha Chintalapani and Suresh Srinivas about OpenMetadata, an open standard for metadata and a reference implementation for a central metadata store
Interview
Introduction
How did you get involved in the area of data management?
Can you describe what the OpenMetadata project is and the story behind it?
What are the goals of the project?
What are the common challenges faced by engineers and data practitioners in organizing the metadata for their systems?
What are the capabilities that a centralized and holistic view of a platform’s metadata can enable?
How would you characterize the current state and progress on the open source initiative around OpenMetadata?
How does OpenMetadata compare to the OpenLineage project and other similar systems?
What opportunities do you see for collaborating with or learning from their efforts?
What are the schema elements that you have identified as critical to a holistic view of an organization’s metadata?
For an organization with an existing data platform, what is the role that OpenMetadata plays, and what are the points of integration across the different components?
Can you describe the implementation of the OpenMetadata architecture?
What are the user experience and operational characteristics that you are trying to optimize for as you iterate on the project?
What are the challenges that you face in balancing the generality and specificity of the core schemas for metadata objects?
There are a large and growing number of businesses that create systems on top of an organizations metadata in the form of catalogs, observability, governance, data quality, etc. What do you see as the role of the OpenMetadata project across that ecosystem of products?
How has your perspective on the domain of metadata management and the associated challenges changed or evolved as you have been working on this project?
What are the most interesting, unexpected, or challenging lessons that you have learned while working on OpenMetadata?
When is OpenMetadata the wrong choice?
What do you have planned for the future of OpenMetadata?
Contact Info
Suresh
LinkedIn
@suresh_m_s on Twitter
sureshms on GitHub
Sriharsha
LinkedIn
harshach on GitHub
@d3fmacro on Twitter
Parting 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 show, Podcast.__init__ to learn about the Python language, its community, and the innovative ways it is being used.
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 hosts@dataengineeringpodcast.com) with your story.
To help other people find the show please leave a review on iTunes and tell your friends and co-workers
Links
OpenMetadata
Apache Storm
Apache Kafka
Hortonworks
Apache Atlas
OpenMetadata Sandbox
OpenLineage
Podcast Episode
Egeria
JSON Schema
Amundsen
Podcast Episode
DataHub
Podcast Episode
JanusGraph
Titan Graph Database
HBase
Jetty
DropWizard
The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA
Support Data Engineering Podcast