Agentic AI in the Wild: What Actually Runs in Production

About this event

AI agents are moving into production. The question is no longer whether to use them, but what it actually takes to make them work once the demo is over.

This WeAreDevelopers PreDay meetup is for builders, founders, and practitioners wiring AI agents into real codebases, CI/CD pipelines, developer platforms, and knowledge systems. The evening focuses on the honest conversations that rarely fit into a conference talk: what breaks at scale, what context engineering really looks like, and where the failure modes hide.
The theme is connected intelligence: how graph-based reasoning, smarter pipelines, and agentic code review are changing production AI systems, and what engineering teams need to do differently to support them.

We will explore constraint satisfaction in agent decision-making, agentic AI in production, AI-powered development workflows, and Java’s role in the future of AI systems. No vendor pitches. Just the stuff that runs in production.

Agenda
17:00 — Doors Open, Drinks and Networking
17:30 — Welcome and Opening Remarks
17:45 — Andreas Kollegger, Director of GenAI, Neo4j
18:10 — Break, Food and Networking
18:35 — Panel Discussion: Agentic AI in the Wild
19:20 — Tech Talk 2: CircleCI
19:45 — Ana Maria Mihalceanu, Java Champion Alumni and Developer Advocate, Oracle
20:25 — Closing Remarks

Speakers and Sessions
Andreas Kollegger, Director of GenAI, Neo4j
Talk: Where is the Zebra? Agent Decision-making as Constraint Satisfaction
Zebra Puzzles are a useful lens for understanding agentic reasoning. They require no domain knowledge, only structured constraint satisfaction. Real-world decisions, however, are messier: loan approvals, resource allocation, compliance, and approval routing often combine hard rules, soft rules, and human discretion.
This session examines how different architectures approach structured decision-making and why recognizing constraint satisfaction problems changes how you build agents. You will learn how constraint networks, LLMs, and hybrid systems solve logical problems differently, how enterprise decisions often hide “Zebra Puzzles” beneath complexity, and when your agent needs search, inference, generation, or a hybrid approach.

Ana Maria Mihalceanu, Java Champion Alumni and Developer Advocate, Oracle
Talk: Now and Next Java for AI
Tired of treating AI as a black-box REST endpoint? With JDK 25 and the Foreign Function and Memory API, Java developers can wire real models directly to native runtimes such as ONNX for fast CPU/GPU inference.
This talk shows how to map tensor buffers to Java MemorySegment, switch execution providers, and build self-contained Java applications for inference. It also looks ahead to Project Babylon’s code reflection, where model logic can be expressed as Java code that can be analyzed and lowered to accelerator backends, reducing the need for external model files or glue languages.
Build expressive and testable FFM-based inference today, and author pure Java AI-ready models tomorrow.

CircleCI Speaker
Details TBC

Panel: Agentic AI in the Wild
What does it take to move AI agents from proof of concept into systems that run reliably? This panel brings together practitioners from across the stack to discuss context management, failure modes, governance, production workflows, and what changes when agentic systems scale.
Expect specific lessons, not talking points.
Moderator
Dana Fine — Open Source and Community Manager, Qodo
Dana leads open-source programs and community at Qodo. She runs the GitHub User Group, CNCF local and GenAI communities, organizes the Bond AI meetup series, and has built developer communities across the cloud native and open source ecosystem for years.
Panelists
Nnenna Ndukwe — Developer Relations Lead, Qodo
Nnenna leads Developer Relations at Qodo, the AI code review platform. She is a software developer, applied AI researcher, and community builder with over a decade of experience across med-tech, fintech, and media-tech. A 2019 Google Women Techmakers Scholar, she focuses on integrating AI code review into modern development workflows for open source and enterprise teams at scale.
Sebastian Kister
Sebastian is a cloud pioneer and enterprise transformation practitioner known for implementing production-ready architecture for Agentic AI Operations in a large enterprise environment. An active CNCF and Linux Foundation member, he advocates for scalable platform ecosystems and a people-first approach: people first, then tools, then processes.