Streaming Context with Kafka & Elasticsearch + Building Real-World Agentic AI

The Elastic Developer Relations team will be in town sponsoring Open Source North and will be hosting a joint meetup with the Twin Cities Apache Kafka® Meetup by Confluent ahead of the conference on Wednesday, May 27

We'll have presentations from Justin Castilla (Sr. Developer Advocate at Elastic) and Sandon Jacobs (Confluent), followed by networking, pizza, and refreshments.

Thank you to Improving for hosting our meetup. Improving is a modern digital services consulting firm focused on solving business problems with innovative technical solutions.

📅 Date and Time:
Wednesday, May 27th, from 5:30-7:30 pm CDT

📍Location:
Improving Minneapolis: 3033 Excelsior Blvd #180, Minneapolis, MN 55416

Enter "Lakeside Center" in Google Maps for the most accurate location.

🪧 Arrival Instructions:
Follow the hallway to the elevators or stairs and go up to the first floor. We are down the hall from the elevators and around the corner from the stairs.

⚡️ Interested in giving a talk? ⚡️
Are you interested in presenting your Elastic use case? We welcome 5-10 minute lightning talks, 45-minute deep dives, and everything in between. If you're interested, please send us an email at meetups@elastic.co.

📝 Agenda:

• 5:30 pm: Doors open
• 6:00 pm: Streaming Context: Powering Semantic Search with Kafka and Elasticsearch - Sandon Jacobs (Confluent)
• 6:30 pm: ​There an back again… but by ferry or I-5? By Justin Castilla (Sr. Developer Advocate at Elastic)
• 7:00-7:30 pm: Networking

💭 Talk Abstracts:
Streaming Context: Powering Semantic Search with Kafka and Elasticsearch - Sandon Jacobs (Confluent)
As the de facto platform for event streaming, we’ve seen how data from Apache Kafka can easily empower basic keyword search. But let's be real, modern semantic search applications need context to interpret the real meaning and intent of a user's query. We could wait around for the next batch job to kick off and provide that context... or we could serve it up in near real-time right from our data streams. In this talk, we'll discuss how to leverage data streams from Kafka to power much smarter semantic search with Elasticsearch. We’ll follow a simple event from a Kafka topic and see how it transforms into a powerful vector embedding. Then, we’ll see this whole flow in action using a k-Nearest Neighbor search to instantly find similar items in milliseconds. While my code examples will be in Java or Kotlin using the Spring Boot and Spring AI ecosystem, FEAR NOT! The core concepts—getting data into a vector format via a stream—are totally language agnostic. Join us to grab a few practical ideas you can take and use in your next project!

​There an back again… but by ferry or I-5? By Justin Castilla (Sr. Developer Advocate at Elastic)
Living on Washington State’s peninsula offers endless beauty, nature, and commuting challenges. In this talk, I’ll share how I built an agentic AI system that creates and compares optimal routes to the mainland, factoring in ferry schedules, costs, driving distances, and live traffic. Originally a testbed for the Model Context Protocol (MCP) framework, this project now manages my travel schedule, generates expense estimates, and sends timely notifications for events. I’ll give a comprehensive overview of MCP, show how to quickly turn ideas into working agentic AI, and discuss practical integration with real-world APIs. Attendees will leave with actionable insights and a roadmap for building their own agentic AI
solutions.