2 Talks : Improving Search with AI & Building Agentic AI with LangChain4j
Detalles
Agenda for the event :
18:15 Welcome
18:30 “Improving Search with AI” by Tetiana Stroganova and Marc Ros
19:10 “From Prompts to Workflow: Building Agentic AI with LangChain4j” by Alex Soto
20:00 Networking with pizza and drinks
21:00 End of the Event
REGISTER in LuMA : https://luma.com/zgyw8wlp
***
# Improving Search with AI
As AI transforms Search, assessing its impact becomes just as important as deploying it. In this session, we’ll unpack our journey to build and evaluate vector search: how embeddings improve recall, how we simulate new changes in Search, and how we use LLMs for large-scale, automated relevance evaluation. Expect real examples, metrics, and lessons learned on creating and evaluating AI-based systems.
## Tetiana Stroganova:
I’m Tetiana Stroganova. I’ve been working with data for ten years, four of which as a Data Scientist. At Ocado Technology, I focus on designing AI-powered solutions to solve search-related challenges.
## Marc Ros:
I'm Marc Ros, a Telecom Engineer from Barcelona. I've spent my entire professional life working in Data. I started as a Data Analyst at Glovo, where I spent almost three years in the Operations and Logistics departments. Later, I decided to continue my studies and completed a Master's in Artificial Intelligence. Since then, I've been working as a Data Scientist at Ocado Technology, focusing on applying AI to improve our search systems.
***
# From Prompts to Workflow: Building Agentic AI with LangChain4j
Large language models are no longer just answering questions. They are becoming agents that plan, call tools, loop until quality is high, and even ask humans for help. This new agentic approach unlocks complex business workflows, but only if developers can use it in a controlled, enterprise-ready way.
In this session, we’ll take a hands-on journey from a simple REST endpoint to a fully functioning agentic workflow powered by the new LangChain4j-agentic module and a local model running with Ollama. You’ll see how to:
> • Define typed Java agents with @Agent.
> • Wire tools into your agents for real business actions
> • Orchestrate multistep workflows with sequence, loop, and parallel patterns
> • Hand off execution to a Supervisor for true autonomous behaviour.
> • Keep everything observable, testable, and ready for production
If you’re a Java developer or architect curious about how to move beyond single-prompt demos and bring agentic AI into enterprise systems, this talk will show you exactly how. It includes runnable Java code, practical design patterns, and the pitfalls to avoid.
## Alex Soto
Alex Soto is a Developer Advocate at IBM. He is passionate about the Java world and software automation and believes in the open-source software model. Alex is the co-author of Manning and O'Reilly books Testing Java Microservice, Quarkus Cookbook, Kubernetes Secrets Management, GitOps Cookbook, RHCE Ansible Automation Study Guide, Applied AI for Enterprise Java Development, and AI Agents with Java.
A Java Champion since 2017, he is also an international speaker (Devoxx, KubeCon, DevNexus, JavaOne, JavaLand, …) and teacher at Salle URL University. You can follow him on Twitter (@alexsotob) to stay tuned to what’s happening in Java.