What does it mean to be agentic? Is there a spectrum of agency?  In this episode of The Analytics Engineering Podcast, Tristan Handy talks to Sean Falconer, senior director of AI strategy at Confluent, about AI agents. They discuss what truly makes software "agentic," where agents are successfully being deployed, and how to conceptualize and build agents within enterprise infrastructure.  Sean shares practical ideas about the changing trends in AI, the role of basic models, and why agents may be better for businesses than for consumers. This episode will give you a clear, practical idea of how AI agents can change businesses, instead of being a vague marketing buzzword. For full show notes and to read 6+ years of back issues of the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.

Send us a text Deep Diving into the future of AI:

Join Dr. Sean Falconer — AI Entrepreneur in Residence at Confluent, software engineering leader, and developer relations expert — for a deep dive into the future of AI, data streaming, and what it really means to build at the edge of innovation. From managing multiple LLMs to testing autonomous agents and sharing his bold contrarian takes, Sean helps us simplify the complexity of today's tech. 📌 Timestamps  04:38 – Meet Sean Falconer 11:11 – Lifelong Learning 12:31 – AI Entrepreneur in Residence 16:28 – Multiple LLMs in Action 21:07 – The Tech Behind Confluent 25:51 – Why Sean Chose Confluent 28:40 – Invest or Short? 36:58 – Testing Agents IRL 40:51 – The Contrarian AI Take 42:27 – Looking Ahead: The Future of AI🔗 Connect with Sean: LinkedInSubstackMedium

Want to be featured as a guest on Making Data Simple? Reach out to us at [email protected] and tell us why you should be next. The Making Data Simple Podcast is hosted by Al Martin, WW VP Technical Sales, IBM, where we explore trending technologies, business innovation, and leadership ... while keeping it simple & fun.

Learn how Confluent simplifies real-time streaming of your SAP data into AI-ready Delta tables on Databricks. In this session, you'll see how Confluent’s fully managed data streaming platform—with unified Apache Kafka® and Apache Flink®—connects data from SAP S/4HANA, ECC, and 120+ other sources to enable easy development of trusted, real-time data products that fuel highly contextualized AI and analytics. With Tableflow, you can represent Kafka topics as Delta tables in just a few clicks—eliminating brittle batch jobs and custom pipelines. You’ll see a product demo showcasing how Confluent unites your SAP and Databricks environments to unlock ERP-fueled AI, all while reducing the total cost of ownership (TCO) for data streaming by up to 60%.

This session unveils Google Cloud's Agent2Agent (A2A) protocol, ushering in a new era of AI interoperability where diverse agents collaborate seamlessly to solve complex enterprise challenges. Join our panel of experts to discover how A2A empowers you to deeply integrate these collaborative AI systems with your existing enterprise data, custom APIs, and critical workflows. Ultimately, learn to build more powerful, versatile, and securely managed agentic ecosystems by combining specialized Google-built agents with your own custom solutions (Vertex AI or no-code). Extend this ecosystem further by serving these agents with Databricks Model Serving and governing them with Unity Catalog for consistent security and management across your enterprise.

Life as a father, tech leader, and fitness enthusiast demands efficiency. To reclaim my time, I’ve built AI-driven solutions that automate everyday tasks—from research agents that prep for podcasts to multi-agent systems that plan meals—all powered by real-time data and automation. This session dives into the technical foundations of these solutions, focusing on event-driven agent design and scalable patterns for robust AI systems. You’ll discover how Databricks technologies like Delta Lake, for reliable and scalable data management, and DSPy, for streamlining the development of generative AI workflows, empower seamless decision-making and deliver actionable insights. Through detailed architecture diagrams and a live demo, I’ll showcase how to design systems that process data in motion to tackle complex, real-world problems. Whether you’re an engineer, architect, or data scientist, you’ll leave with practical strategies to integrate AI-driven automation into your workflows.

When was the last time you performed a mathematical operation on an email address? Or multiplied a credit card number by a passport number?

It's absurd, this would be an insane thing to do, yet we keep storing sensitive customer information in our data warehouses, risking PII exposure, as if we need to perform operations like this. This forces our data teams to act as data police, controlling access—a job that's the definition of “not fun” and quickly becomes unmanageable. Companies are then faced with the difficult choice of either locking down all access or granting over-privileged access, neither of which is ideal.

But what if there's a better way?

In this talk, we'll explore how leading tech companies with the largest amount of customer data solve this problem. We'll look at the architectural patterns they use to balance data security and usability, and how these solutions can free our data teams from their policing duties.

Summary The best way to make sure that you don’t leak sensitive data is to never have it in the first place. The team at Skyflow decided that the second best way is to build a storage system dedicated to securely managing your sensitive information and making it easy to integrate with your applications and data systems. In this episode Sean Falconer explains the idea of a data privacy vault and how this new architectural element can drastically reduce the potential for making a mistake with how you manage regulated or personally identifiable information.

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 new managed database service you can launch a production ready MySQL, Postgres, or MongoDB cluster in minutes, with automated backups, 40 Gbps connections from your application hosts, and high throughput SSDs. Go to dataengineeringpodcast.com/linode today and get a $100 credit to launch a database, create a Kubernetes cluster, or take advantage of all of their other services. And don’t forget to thank them for their continued support of this show! Atlan is the metadata hub for your data ecosystem. Instead of locking all of that information into a new silo, unleash its transformative potential with Atlan’s active metadata capabilities. Push information about data freshness and quality to your business intelligence, automatically scale up and down your warehouse based on usage patterns, and let the bots answer those questions in Slack so that the humans can focus on delivering real value. Go to dataengineeringpodcast.com/atlan today to learn more about how you can take advantage of active metadata and escape the chaos. Modern data teams are dealing with a lot of complexity in their data pipelines and analytical code. Monitoring data quality, tracing incidents, and testing changes can be daunting and often takes hours to days or even weeks. By the time errors have made their way into production, it’s often too late and damage is done. Datafold built automated regression testing to help data and analytics engineers deal with data quality in their pull requests. Datafold shows how a change in SQL code affects your data, both on a statistical level and down to individual rows and values before it gets merged to production. No more shipping and praying, you can now know exactly what will change in your database! Datafold integrates with all major data warehouses as well as frameworks such as Airflow & dbt and seamlessly plugs into CI workflows. Visit dataengineeringpodcast.com/datafold today to book a demo with Datafold. Data teams are increasingly under pressure to deliver. According to a recent survey by Ascend.io, 95% in fact reported being at or over capacity. With 72% of data experts reporting demands on their team going up faster than they can hire, it’s no surprise they are increasingly turning to automation. In fact, while only 3.5% report having current investments in automation, 85% of data teams plan on investing in automation in the next 12 months. 85%!!! That’s where our friends at Ascend.io come in. The Ascend Data Automation Cloud provides a unified platform for data ingestion, transformation, orchestration, and observability. Ascend users love its declarative pipelines, powerful SDK, elegant UI, and extensible plug-in architecture, as well as its support for Python, SQL, Scala, and Java. Ascend automates workloads on Snowflake, Databricks, BigQuery, and open source Spark, and can be deployed in AWS, Azure, or GCP. Go to dataengineeringpodcast.com/ascend and sign up for a free trial. If you’re a data engineering podcast listener, you get credits worth $5,000 when you become a customer. Your host is Tobias Macey and today I’m interviewing Sean Falconer about the idea of a data privacy vault and how the Skyflow team are working to make it turn-key

Interview

Introduction How did you get involved in the area of data management? Can you describe what Skyflow is and the story behind it? What is a "data privacy vault" and how does it differ from strategies such as privacy engineering or existing data governance patterns? What are the primary use cases and capabilities that you are focused on solving for with Skyflow?

Who is the target customer for Skyflow (e.g. how does it enter an organization)?

How is the Skyflow platform architected?

How have the design and goals of the system changed or evolved over time?

Can you describe the process of integrating with Skyflow at the application level? For organizations that are building analytical capabilities on top of the data managed in their applications, what are the interactions with Skyflow at each of the stages in the data lifecycle? One of the perennial problems with distributed systems is the challenge of joining data across machine boundaries. How do you mitigate that problem? On your website there are different "vaults" advertised in the form of healthcare, fintech, and PII. What are the different requirements across each of those problem domains?

What are the commonalities?

As a relatively new company in an emerging product category, what are some of the customer education challenges that you are facing? What are the most interesting, innovative, or unexpected ways that you have seen Skyflow used? What are the most interesting, unexpected, or challenging lessons that you have learned while working on Skyflow? When is Skyflow the wrong choice? What do you have planned for the future of Skyflow?

Contact Info

LinkedIn @seanfalconer on Twitter Website

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 [email protected]) with your story. To help other people find the show please leave a review on iTunes and tell your friends and co-workers

Links

Skyflow Privacy Engineering Data Governance Homomorphic Encryption Polymorphic Encryption

The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA

Support Data Engineering Podcast