Sessions

Talk · 25 min

"YOU MUST NOT ssh!" and Other Stories from Building Our SRE Agent

Everyone is building SRE agents. Most of them are barely junior sysadmins in a trench coat — useful for "how…

09:20 · Studio 4

David Pech Wrike

Lessons Learned & Anti-Patterns · AI Observability & Production · AI for Legacy & Refactoring

Lightning Talk · 7 min

A Practical Guide to Fast and Private LLMs

A set of practical tips and tools for hobbyists and teams to run their own LLM in a private and sustainable setup…

12:20 · Millennium

Lena Fuhrimann bespinian

Local AI, Inference & Open Models

Hands-On Session · 75–90 min

ADK Crash Course - From Beginner To Expert

You're about to step into the exciting world of AI agents. Forget simple chatbots that just answer questions…

13:00 · Studio 3 AB

Abdel Sghiouar Google Cloud

Agent Frameworks · Multi-Agent Architectures · MCP & Agent Protocols

Hands-On Session · 75–90 min

Agent on the Wire: Looking Inside an AI Coding Agent

What actually happens between giving an AI coding agent a task and receiving working software? In this hands-on…

15:20 · Studio 1

Vincent G letsboot

Lessons Learned & Anti-Patterns · Agent Frameworks · AI Evals & Testing · AI Observability & Production · AI Coding Tools

Talk · 25 min ★ Spotlight · Migros Online

Agentic AI at Migros Online: Autonomous Engineering Agents and Conversational Shopping

AI agents are arriving at both ends of e-commerce at once. Inside product engineering organizations, they are…

15:20 · Studio 4

Sven Scheffel Migros Online

Gabriel Dinant Migros Online

Lessons Learned & Anti-Patterns · MCP & Agent Protocols · Software Architecture with AI · Enterprise AI Adoption & Governance · Industry & Vertical Use Cases

Talk · 25 min

Agents Need Platforms Too: Running LLM and Agent Workloads the Cloud-Native Way

Demos of AI agents are easy. Running them reliably is not. Once agents move from local experiments into…

13:40 · Studio 6

Aarno Aukia VSHN

MCP & Agent Protocols · AI Observability & Production · AI Security · Local AI, Inference & Open Models · AI in DevOps & Platform Engineering

Talk · 25 min

Agents Speak Protocol: Why Standards Are the Real Infrastructure of AI

Every major computing revolution eventually standardized how things talk to each other. Before TCP/IP, networks…

11:00 · Millennium

Stefano Maestri IBM

Alessio Soldano IBM

Agent Frameworks · Multi-Agent Architectures · MCP & Agent Protocols

Talk · 25 min

AI & Agility: Is Spec-Driven Development Bringing Back Waterfall? And How to Move Beyond It

With the rise of LLMs, a new promise has emerged: software development driven by specifications. Multi-agent…

13:00 · Millennium

Baptiste Macé Arolla

AI-Assisted Coding Practice

Talk · 25 min ★ Spotlight · Exasol

Beyond MCP - Supercharging your agents with a single unified data plane

Agents need context that's spread across many systems, and regulated organisations can't copy it all into one AI…

10:20 · Studio 6

Alexander Stigsen Exasol

MCP & Agent Protocols · RAG & Knowledge Retrieval

Talk · 25 min

Beyond Prompts & Models: Evolving Architecture for Agentic Systems

As organizations experiment with enterprise agentic systems, discussions often center on models, frameworks, and…

10:20 · Millennium

Manisha De Swisscom

Lessons Learned & Anti-Patterns · Agent Frameworks · Multi-Agent Architectures · MCP & Agent Protocols · RAG & Knowledge Retrieval · AI Coding Tools · Software Architecture with AI

Talk · 25 min

Build your own Coding Agent

Coding agents feel like magic: point one at a codebase, ask it to fix a bug, and it reads files, edits code, runs…

15:20 · Millennium

Max Gfeller Lovable

MCP & Agent Protocols · AI Coding Tools · AI-Assisted Coding Practice · Software Architecture with AI

Hands-On Session · 75–90 min

Build Your Own Production-Ready Agentic Apps

Most agentic AI demos stop at "hello world." In this lab, attendees will build a real agentic application using…

13:00 · Studio 1

Kevin Dubois IBM

Dimitris Andreadis Red Hat / IBM

Agent Frameworks · Multi-Agent Architectures

Talk · 25 min

Building Authorization for Agentic RAG Systems

We’ve recently seen the rise of Retrieval Augmented Generation (RAG) systems. With the proliferation of AI…

11:00 · Studio 4

Sohan Maheshwar AuthZed

RAG & Knowledge Retrieval · AI Security · Enterprise AI Adoption & Governance

Panel Discussion · 25 min

Can We Trust Autonomous Agents? (Panel Discussion)

Panel discussion. How much autonomy can we hand to agents in production — and what has to be in place before we…

15:20 · Studio 3 AB

Maxim Salnikov Microsoft

Jose Luis Latorre Millas Swiss Life

Serena Sensini TheRedCode

Markus Leutwyler VisionPilot

Lize Raes LangChain4j

AI Evals & Testing · AI Observability & Production · AI Ethics & Responsibility

Talk · 25 min

Deploying Agents at Scale: What Enterprise Adoption Actually Looks Like

I spend my days inside enterprise AI rollouts — standing up the platforms, watching what agents do at scale, and…

10:20 · Studio 4

Michael Rishi Forrester Accenture

Lessons Learned & Anti-Patterns · AI-Assisted Coding Practice · Enterprise AI Adoption & Governance · AI Strategy & Value Realization

Lightning Talk · 7 min

From a RAG Demo to a RAG System

Building a RAG demo is easy. Making it reliable is a different challenge. Real-world RAG systems face messy…

12:28 · Millennium

Richa Dinesh Tamhane amnis

Lessons Learned & Anti-Patterns · RAG & Knowledge Retrieval

Talk · 25 min ★ Spotlight · re:cinq

From Copilot to the Dark Factory

AI coding tools make developers faster, but they do not automatically make organisations ship faster. PR volume…

13:00 · Studio 4

Pini Reznik re:cinq

Multi-Agent Architectures · Spec-Driven & Agentic SDLC · Enterprise AI Adoption & Governance

Talk · 25 min ★ Spotlight · Atlassian

FSI Transformation at Scale: Sovereignty, Compliance & Production Realities

Every financial institution aspires to become 'AI-native.' They promise hyper-automated engineering, autonomous…

15:20 · Studio 6

Sergiu Petean Atlassian

Baris Yorganci BarmeniaGothaer

Hands-On Session · 75–90 min

Hands-on Spec-Driven Development

In this lab, participants will learn how to develop software efficiently and systematically using Spec-driven…

10:20 · Studio 1

Simon Martinelli martinelli.ch

Lessons Learned & Anti-Patterns · Spec-Driven & Agentic SDLC

Talk · 25 min ★ Spotlight · LogicStar

How do you know your coding agent actually helps?

Agents now write most PRs in many teams. Often another agent reviews them. Yet almost nothing merges without a…

16:00 · Studio 4

Boris Paskalev

Lessons Learned & Anti-Patterns · AI Evals & Testing · AI-Assisted Coding Practice · Spec-Driven & Agentic SDLC

Talk · 25 min

Human-in-the-Loop Is You: A Guide to Working With Multiple Coding Agents

"Human-in-the-loop" is supposed to mean a person makes the judgment calls a model can't. In practice, when Claude…

16:00 · Millennium

Oleksandra Bovkun Databricks

Lessons Learned & Anti-Patterns · AI Coding Tools

Hands-On Session · 75–90 min

Just Build — Orchestrating your Agents with Codex

A hands-on lab guided by OpenAI: see how you can orchestrate your agents with Codex. Follow along step by step on…

10:20 · Studio 3 AB

Abbas Tutcuoglu OpenAI

Arsenii Gavrilenko OpenAI

Jules Giroul OpenAI

Agent Frameworks · AI Coding Tools · AI-Assisted Coding Practice

Talk · 25 min

Migration or migraine: What no one tells you about using LLMs

We had a task stuck forever in our backlog. A task so simple, yet so tedious that our team just kept postponing…

09:20 · Studio 3 AB

Warren Parad Authress

Lessons Learned & Anti-Patterns · Spec-Driven & Agentic SDLC

Talk · 25 min ★ Spotlight · copebit

Millions of exceptions a day: getting Bedrock and AgentCore right

BLP Digital's agentic platform resolves millions of exceptions a day across 550+ enterprise customers in 40+…

09:20 · Millennium

Marco Kuendig copebit

Davide Walder BLP Digital

Multi-Agent Architectures · AI Security · Enterprise AI Adoption & Governance

Talk · 25 min

NOOA: Inside NVIDIA's Object-Oriented Agent Harness

An agent is only as good as the harness around the model. At NVIDIA, Matt's team built NOOA (NVIDIA Labs…

11:40 · Millennium

Ricardo Silveira Cabral NVIDIA

Matt Staats NVIDIA

Agent Frameworks

Talk · 25 min

OCR at Swiss Post: The Case for Small Language Models

Everyone reaches for a frontier LLM by default — and then the bill, the latency, and the data-privacy questions…

14:20 · Studio 4

Huriel Reichel Swiss Post

Oliver Hofmann Swiss Post

Local AI, Inference & Open Models · Software Architecture with AI · Enterprise AI Adoption & Governance

Talk · 25 min ★ Spotlight · TD SYNNEX

Open Agentic AI Without Lock-In: The IBM Approach with watsonx Orchestrate

Agentic AI is transforming how organizations automate work, but many solutions come with platform dependencies and…

14:20 · Studio 6

Domenic Largiadèr IBM

Multi-Agent Architectures

Talk · 25 min

Reachy mini: Giving a body to AI

Large language models can reason, generate code, and hold conversations. But they remain trapped behind screens…

08:45 · Millennium

Andrés Marafioti Hugging Face

Local AI, Inference & Open Models · Voice & Multimodal Agents · Industry & Vertical Use Cases

Lightning Talk · 7 min

Running Secure Agents at Scale

Building secure and scalable agents at scale is hard. From multi-tenancy and noisy-neighbor risk to tool access…

12:36 · Millennium

Alex Carol Adobe

Lessons Learned & Anti-Patterns · Agent Frameworks · AI Security · AI Community, Open Source & Education

Lightning Talk · 7 min

Securing MCP in the Enterprise: OAuth, Token Exchange, and Real-World CI/CD Integration

This talk shares a hands-on experience integrating the Model Context Protocol (MCP) into an enterprise CI/CD…

12:44 · Millennium

Valentin Delaye ELCA

MCP & Agent Protocols

Talk · 25 min ★ Spotlight · AWS

Specs first, code later (or how I build software in the AI-DLC era)

As AI-driven software development became part of our lives, writing specs before touching anything code-related…

11:40 · Studio 4

Alessandra Pasini AWS

Talk · 25 min

The Agentic Lab Factory: How I Stopped Writing Labs and Started Reviewing Them

For years, getting new contributor SMEs to write labs was an uphill battle. The learning curve was too steep, the…

09:20 · Studio 6

Raphaël Pinson Isovalent

AI Evals & Testing · AI-Assisted Coding Practice

Talk · 25 min

The next frontier - agentic collaborative environments.

AI-agentic developer tools like Claude Code or GitHub Copilot CLI have emerged as a primary way to develop…

13:40 · Millennium

Krzysztof Cieślak GitHub Next

AI Product UX & Human-Agent Collaboration

Talk · 25 min ★ Spotlight · Flagsmith

Tie a Metric to Every Release

AI writes more of our code every week, which means we ship a lot more than we used to. But we don't fly blind…

11:00 · Studio 6

Matt Elwell Flagsmith

Lessons Learned & Anti-Patterns · AI Observability & Production · AI Coding Tools

Talk · 25 min

Watching Agents for Trouble

Once an agent can touch a database, send email, or deploy something, the interesting question shifts from "is the…

13:40 · Studio 4

Natalie Pistunovich JFrog

Multi-Agent Architectures · AI Observability & Production · AI Security

Talk · 25 min

We Rolled Out GitHub Copilot… How Do We Prove It Helps?

AI-assisted development tools like GitHub Copilot are being adopted quickly. Many organizations have already…

13:00 · Studio 6

Yuliya Khadasevich Eneco

Liuba Gonta Xebia

Lessons Learned & Anti-Patterns · AI Coding Tools · Enterprise AI Adoption & Governance · AI Strategy & Value Realization

Lightning Talk · 7 min

Welcome Session

Doors open, coffee's poured — let's kick things off. Join Barbara and Jonas Felix, co-founders of letsboot, as…

08:30 · Millennium

Jonas Felix Co-Founder Agentic Days / letsboot.ch

Barbara Felix Co-Founder Agentic Days / letsboot.ch

Talk · 25 min

When Software Stops Being Deterministic: Rethinking Engineering Practices for AI-Native Systems

For decades, we've built software around a simple assumption: the same input produces the same output. If behavior…

14:20 · Millennium

Susanna Wong Typeform

Lessons Learned & Anti-Patterns · Multi-Agent Architectures · AI Evals & Testing · AI Observability & Production

Talk · 25 min

You Can't Ctrl-Z a Robot: Coding Agents in Embedded Systems

Coding agents work well in the terminal because feedback there costs nothing. Compiler errors, failing tests…

11:40 · Studio 6

Syrian Hadad adesso Schweiz

Alexander Büchel adesso Schweiz

Lessons Learned & Anti-Patterns · AI Evals & Testing · AI-Assisted Coding Practice

Talk · 25 min

Your Biggest New Customer Can't See Pixels

For decades we've argued that accessibility is the right thing to do. The argument just got a lot easier, because…

14:20 · Studio 3 AB

Tim Damen ABN AMRO

AI Product UX & Human-Agent Collaboration · AI Ethics & Responsibility