Queues for Apache Kakfa® x How MCP Bridges LLMs and Data Streams

Join us for a meetup on Wednesday, February 4th from 6:00pm in Milan hosted by Bitrock!

📍Venue:
Bitrock
Via Tortona, 4, 20144 Milano MI, Italy. 1st Floor.

**IMPORTANT: There are limited seats, so if you cannot attend, please change your RSVP so someone else can join. Thanks!***

🗓 Agenda:

• 6:15pm: Doors open/Welcome
• 6:30pm - 6:45pm: Simone Esposito, Team Lead - Software Architect @ Bitrock
• 7:00pm - 7:45pm: Viktor Gamov, Principal Developer Advocate, Confluent
• 7:30pm - 8:00pm: Additional Q&A, Drinks, Food and Networking

💡 First Speakers:
Simone Esposito, Team Lead - Software Architect @ Bitrock

Title of Talk:
Queues for Kafka (KIP-932)

Abstract:
For more than a decade, Apache Kafka’s consumption model has been governed by a strict rule: one consumer per partition within a consumer group. This limitation has shaped how teams scale their systems, design topics, and plan for peak throughput. With KIP-932, Kafka breaks this long-standing assumption and introduces a fundamentally new capability: queues. Backed by the new concept of share groups, this paradigm shift allows multiple consumers to read concurrently from the same partition.

This talk explores how KIP-932 brings native queueing semantics to Kafka, enabling true work-queue patterns without over-partitioning and greatly simplifying horizontal scaling. We’ll examine how the new message acknowledgment model works, the tradeoffs introduced by cooperative consumption, and how this feature fits alongside, and differs from, traditional Kafka consumer groups.

Bios:
Simone Esposito is Software Architect & Team Lead at Bitrock. Passionate about computer science, Simone is always excited to test himself with different technologies and learn new things. He has a strong passion for writing code and sharing knowledge with colleagues and peers in the industry. He prefers working with functional programming languages, distributed systems and event-driven architectures.

💡 Second Speaker:
Viktor Gamov, Principal Developer Advocate, Confluent

Title of Talk:
The Missing Protocol: How MCP Bridges LLMs and Data Streams

Abstract:
Nobody’s talking about this: MCP isn’t just another way to build chatbots. It’s the bridge we’ve been missing between AI reasoning and real-time data systems. Teams build AI applications that work great in demos but fall apart with production data. Your agents analyze historical reports but can’t tell what’s happening in your Kafka streams. They’re blind to schema changes and disconnected from events that matter to your business. Instead of treating streaming platforms like black boxes, you expose them directly to your agents via MCP protocol. Suddenly, your AI doesn’t just read about data—it lives inside your data flows. Learn what becomes possible when you stop thinking about AI as an external service and start treating it as part of your streaming architecture. We’ll build systems where agents subscribe to real-time events, reason about evolving schemas, and make decisions that ripple through your data platform.

Bio:
Viktor Gamov is a Principal Developer Advocate at Confluent, founded by the original creators of Apache Kafka®. With a rich background in implementing and advocating for distributed systems and cloud-native architectures, Viktor excels in open-source technologies. He is passionate about assisting architects, developers, and operators in crafting systems that are not only low in latency and scalable but also highly available.

As a Java Champion and an esteemed speaker, Viktor is known for his insightful presentations at top industry events like JavaOne, Devoxx, Kafka Summit, and QCon. His expertise spans distributed systems, real-time data streaming, JVM, and DevOps.

Viktor has co-authored "Enterprise Web Development" from O'Reilly and "Apache Kafka® in Action" from Manning.

Follow Viktor on X - @gamussa to stay updated with Viktor's latest thoughts on technology, his gym and food adventures, and insights into open-source and developer advocacy.

***
NOTE: We are unable to cater for any attendees under the age of 21.
If you would like to speak or host our next event please let us know! community@confluent.io