Deep Research, Agent Memory & Optimizations - The OpenSearch Meetup Amsterdam

Zeta Alpha invites the Gen AI and Search community in Amsterdam to join our next meetup!

We'll kick off at 18:00 with Pizza, Refreshments, Talks, and Networking (this is an in-person only event).

This edition dives into timely, high-impact topics shaping today's AI landscape, featuring speakers from AWS, Eliatra, and Zeta Alpha. Don't miss out!

What our group is about:
We are a community in the Amsterdam area with keen interest in Generative AI, Search Engineering, and Open-Source Technology. Whether you are building production systems or simply curious about the latest and greatest in AI and Search technologies -- such as Agents, MCP, RAG, Fine-Tuning, Vector Search -- this is the space for you!
We welcome all skill levels. Come learn and connect with other cracked engineers.

Time and location:
📅 August 27th, 2025 from 18:00 to 20:30.
📍AWS Office, Mr.Treublaan 7, 4th floor, 1097 DP, Amsterdam.

Schedule:
18:00 -- Arrival. Grab some 🍕 and 🥤.
18:30 -- Community and Contribution - Kris Freedain (AWS).
18:55 -- Keeping the conversation going: Building Persistent LLM Chat Memory with OpenSearch - Lucas Jeanniot (Eliatra)
19:20 -- Moving away from vibes: Automatically optimizing agents for deep research - Arthur Câmara (Zeta Alpha).
19:45 -- Networking with drinks.
20:30 -- Closing.

Talks:

Community and Contribution
OpenSearch Community - learn about the project, the community, and different ways you can contribute and help it grow.

Speaker: Kris Freedain, Community Manager for the OpenSearch Project & OpenSearch Software Foundation technical steering committee.
Kris has decades of experience in tech, but finds connecting people to be the most fulfilling part of being a community professional. Kris is also a Fediverse admin for the Fosstodon instance and serves as a Fosstodon Foundation Board Member.

Keeping the conversation going: Building Persistent LLM Chat Memory with OpenSearch
How can an AI-powered chatbot maintain context over the long haul? This session will explore the practical steps for setting up and managing a local LLM conversation “memory” using OpenSearch’s memory API and indexing. We’ll cover how to store, retrieve, and update both short- and long-term chat context—ensuring your large language model can pick up right where it left off. Attendees will learn techniques for structuring data, handling indexing, and designing memory architectures that result in more contextual, personalized, and durable AI interactions.

Speaker: Lucas Jeanniot, Machine Learning Engineer at Eliatra.

Moving away from vibes: Automatically optimizing agents for deep research
In this talk, we will discuss how to optimize complex, multi-agent systems without relying only on vibes or the good old “LGTM” metric. Instead, we will show how to allow an agent to explore multiple options and re-write it’s prompts by self-reflecting in its own successes and failures, improving its own prompts to specialize in the specific types of queries and corpus it will encounter in production.

Speaker: Arthur Câmara, Research Engineer at Zeta Alpha.