Building Real-Time AI Agents with Elasticsearch and Kafka

## Details

We’re thrilled to unite the Elastic and Confluent communities for an evening of learning and connection.

If you’re deep into Elastic and Kafka or just curious about what’s possible when they come together, this meetup is for you. Expect real-world insights, lively conversations, and plenty of opportunities to connect with fellow developers and data enthusiasts.

IMPORTANT: There are two Lynwood Breweries; this event will be at the Whitaker location.

Agenda:
5:30 - Doors open; come in, meet some people, grab some food
5:45 - Building Data-Grounded AI Agents with Elastic Agent Builder, by Tanya Kalich, Senior Solutions Architect at Elastic
6:15 - Q&A with Tanya
6:30 - Break
6:45 - Streaming Context: Powering Semantic Search with Kafka and Elasticsearch, by Sandon Jacobs, Senior Developer Advocate at Confluent
7:15 - Q&A with Sandon
7:30 - Event wrap up

When:
November 6th
5:30 pm - 7:30 pm

Where:
Lynnwood Brewing Concern
Barrel Room
1053 E. Whitaker Mill Rd

Abstracts:

Building Data-Grounded AI Agents with Elastic Agent Builder
The shift to enterprise AI agents requires a foundation of fresh, high-velocity data. This talk explores the complete, real-time data loop, beginning with Confluent/Kafka streams that reliably feed live logs, metrics, and security events into the Elastic Stack. We will dive into making the most of this data using the Elastic Agent Builder, Elastic’s new platform designed to transform this continuously updated Elasticsearch data into active, conversational partners. We will explore how technical practitioners can leverage the Agent Builder to create specialized AI experts—such as a cybersecurity analyst or a site reliability engineer—by defining custom Tools. A primary focus will be on defining these tools using ES|QL (Elasticsearch Query Language), demonstrating how parameterized, optimized queries operate over real-time data and serve as deterministic guardrails for the Large Language Model (LLM). Attendees will leave with a clear understanding of how to use Elastic in building a high-velocity, data-grounded AI agent ecosystem.

Streaming Context: Powering Semantic Search with Kafka and Elasticsearch
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 session, we'll dive into 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!

Spots are limited, so don't miss out!