​About the Event

​Join us for an evening exploring how real-time data, lakehouse architectures, and streaming systems are powering the next generation of AI and agentic applications. This evolution is driving the convergence of streaming data platforms, lakehouses, and AI infrastructure to enable intelligent systems that can understand, reason about, and respond to the world in real time.

​We'll bring together AI, data, and developer communities to explore the technologies, architectures, and best practices behind modern real-time AI systems.

​Speakers from RisingWave, MotherDuck, and Lenses will share insights into building production-ready real-time AI systems, processing live data streams, enabling operational intelligence, and delivering the right context to AI applications when it matters most.

​Agenda

​6:00 PM – 6:30 PM | Welcome, Networking & Refreshments

​Meet fellow attendees, connect with speakers, and enjoy refreshments before the sessions begin.

​6:30 PM – 7:30 PM | Speaker Sessions

Streaming-first approach to Iceberg with RisingWave

​Rayees Pasha, CPO at RisingWave

This session will provide an overview on the technical challenges of providing a new Iceberg Table engine purpose-built for streaming workloads. The talk will highlight how our team has built end-to-end key capabilities for Iceberg table management, including Iceberg's merge-on-read query, Serverless Compaction and Iceberg table sharing to allow direct queries from other engines. A key feature in this project is the native Iceberg compaction service written in Rust using Apache DataFusion and Apache Iceberg-Rust as foundational components.

​Why Your Lakehouse Should Commit 30x Faster
Bev (Verna) Turnbaugh, Customer Engineer, at MotherDuck

DuckLake: the ideal Kafka consumer for high-volume streams, committing up to 30x/second vs. Iceberg's 1 because metadata lives in a database, not files. Sub-second queries let one table ingest the stream while serving analytics and live AI context. One landing-and-serving layer, exactly what real-time AI needs.

Your Agent's Context Is Stale: Real-Time Context Engineering with Kafka

​Tun Shwe, AI Lead at Lenses

Every source on agentic engineering agrees on one thing: engineering agents are only as good as the context they receive. So where does that context come from? The industry recommends design documents, code repositories, knowledge bases, vector stores, AGENTS.md and other Markdown files. These are all important but they are static artefacts; they tell agents how the world looked when someone last wrote something down. This session will show you how to bring real-time context from Apache Kafka to your agents.
We'll trace the evolution of coding tools through history and then bring the discussion to the present day, sharing how teams can use MCP and skills to practice agentic engineering with real-time data streams.

​7:30 PM – 8:00 PM | Community Networking Reception

​Continue the discussion with speakers and fellow attendees, exchange ideas, and build new connections within the Bay Area AI and data community.

​We look forward to welcoming you for an evening of learning, conversation, and community as we explore the technologies shaping the future of real-time AI.

​RisingWave, MotherDuck, and Lenses co-host this meetup.