Applying AI Events in Cologne

Join us for our second OBI Tech Talk in October!

⏰ Event-Details:
Doors open: from 6pm

18:30 PM - “Event Sourcing for AI Agents: Designing harnesses that survive Production”
Bruno Bonando - Director of Technology @ Intellias
19:15 PM - “Centralised business logic in decentralized architecture”
Michaël Le Barbier - Data & AI Engineer @ Thoughtworks
20:00 - Open discussion, casual networking & pizza!

Location: OBI Office, Carlswerk, Cologne
Talk Language: English 🇬🇧
Cost: Free admission.

Talk 1: Event Sourcing for AI Agents
Designing harnesses that survive Production
AI agents that work in a demo often struggle in production. Retries, partial failures, changing tool outputs and audit requirements quickly expose the limits of a simple prompt-and-loop design.
This session shows how event sourcing gives an agent harness a solid foundation. Every decision, tool call, and state change becomes an immutable event, so agent runs can be replayed, debugged, audited, and recovered after failure. We walk through the architecture and look at code samples for the core building blocks: the event log, projections, idempotent tool execution, and replay-based debugging and evaluation. You leave with a concrete pattern you can apply to your own agent systems.

Bruno Bonando (Director of Technology @ Intellias)
Bruno Bonando is Director of Technology at Intellias, where he leads the Retail practice for the DACH region. With more than 23 years of engineering leadership, he helps companies move AI from pilot to production across engineering, business operations, and product, with particular depth in retail and commerce. He still writes code and runs production systems himself.

Talk 2: Centralised business logic in decentralized architecture
In a monolithic or centralized architecture, a piece of business logic can be owned by a specific component and present an artefact that software engineers and product owners can easily reason about to explain or understand the behavior of the software.
In a microservice or decentralized architecture, such a code artefact vanishes as the business logic is diluted in the service mesh. Traces can recreate a tangible artefact displaying the logic result on a specific run, but they do not carry the same explainability weight as an actual procedure capturing the business logic, which makes it very difficult to reason about modifications.
In this talk, Michaël illustrates the problem with a lab example from retail, explains why monads show up naturally in a decentralized setup but have poor engineering properties, and shows how to extend the compiler to get the best of both worlds (example in Common Lisp).

Michaël Le Barbier (Data & AI Engineer @ Thoughtworks)
Michaël Le Barbier is a Data & AI Engineer at Thoughtworks, combining his strong background as a professional mathematician, programmer, and data specialist with a Math PhD, an Agrégation de Mathématiques, and Max Planck Alumni status. He specializes in software architecture, decentralized systems, and data engineering, bridging the gap between high-level architectural design and practical implementation using clean abstractions and robust engineering practices.

Parking: You can park directly in front of our main entrance (please do not park near the E-Werk). Please find a detailed map with coordinates here.
Exit in the evening: As some gates are closed in the evening, please use the gate near Teltec Köln, Schanzenstraße 29, to leave the premises.

Disclaimer: By attending, you agree that photos and videos taken during the event may be used on social media platforms such as LinkedIn to promote future events.

Hi folks,

Microsoft & Elastic asked me to give a shout out to their event:
https://luma.com/iml0fztu

Tech Talk: Ship Agents, Pass Risk Review: Microsoft Foundry + Elastic on Azure
Speaker: Mike Richter, Principal Partner Solution Architect at Microsoft
Abstract: In this session, I’ll share how I built ELK Burgers, an agent-governance demo using Microsoft Foundry Hosted Agents and Elastic on Azure, and the lessons learned moving toward production readiness. Using synthetic contracts and operating manuals for a fictional restaurant chain, we’ll ask the same question of an intentionally over-permissioned assistant and four agents scoped for different jobs.

​Tech Talk: RAG is Broken: How Elastic & Azure Fix Context, Latency, and Token Bills
Speaker: Francois Protopapa, Principal Solutions Architect at Elastic
Abstract: In this session, we will explore how advanced Context Engineering and Elastic’s hybrid retrieval optimize context accuracy—drastically cutting prompt size, response latency, and cloud API overhead. Furthermore, learn how Elastic LLM Observability (built on OpenTelemetry) delivers total operational visibility, allowing leaders to track token spend, monitor accuracy, and govern AI investments on Azure in real time.

⚠️ Wichtiger Hinweis: Ein RSVP auf Meetup allein reicht leider nicht aus. Bitte registriere dich zusätzlich über die offizielle Eventseite von INFOMOTION. Das hilft uns bei der Planung und spart dir Zeit beim Einlass vor Ort.

👉 Registrierung: https://www.infomotion.de/events/data-ai-meetup-koeln-8e199b53

📅 03.11.2026 | INFOMOTION Innovation Lab Köln

Data & AI erleben. Praxiswissen mitnehmen. Netzwerk erweitern.
Freue dich auf einen inspirierenden Abend mit Expert:innen, Praktiker:innen und Entscheidern aus den Bereichen Data, Analytics und Künstliche Intelligenz. Dich erwarten spannende Praxisvorträge, interessante Diskussionen und ausreichend Zeit zum Netzwerken.

Agenda
🕕 17:30 Uhr – Open Doors, Pizza & Drinks
🎤 18:00 Uhr – Offizieller Start
📊 18:05 Uhr – Fachvorträge
🤝 20:15 Uhr – Networking
🏁 21:00 Uhr – Ende der Veranstaltung

Vorträge
Talk to Your Data: Vom Click-Ops zum Voice Interface, Ein Praxisbericht darüber, wie Lotum den Weg von manuellen BI-Analysen hin zu agentenbasierten Interfaces gegangen ist und welche Ansätze dabei funktioniert haben. Fabian Hadiji, Head of BI @ Lotum

Agentische KI: Vom Millenniumproblem zum Enterprise-Workflow
Wie agentische KI durch koordinierte Agenten, Tool-Nutzung und kontrollierte Workflows neue Möglichkeiten eröffnet und sich gleichzeitig sicher und produktiv im Unternehmen einsetzen lässt. Assoc. Prof. Dr. Marcus Becker, Hochschullehrer für „Digitale Transformation und Technologiemanagement“ am Department für „Business & Management“ vom Management Center Innsbruck (MCI)

AI Agents Everywhere – How Do You Manage Them?
Wie Unternehmen AI Agents zentral verwalten, transparent steuern und skalierbar governieren können, unabhängig davon, wo diese entwickelt wurden.
Arthur Goehrich, Senior Sales Engineer @ Dataiku

Your Agents Are Burning Tokens: Caching, Context and Model Routing in the Wild
Agents burn tokens by paying for the same context again and again. We experimented on a real agent fleet and share what worked: smarter caching, leaner context, and automatic model routing that matches the right LLM to the right task. Practical strategies, honest lessons, no hype. Andrei Beliankou, Technical Product Owner @ E.ON & Evgenia Urban, Senior GenAI Engineer @ E.ON

Networking & Austausch
Nach den Vorträgen bleibt ausreichend Zeit zum Austausch mit anderen Data-&-AI-Interessierten, den Speakern und dem INFOMOTION-Team. Nutze die Gelegenheit, neue Kontakte zu knüpfen und über aktuelle Trends und Herausforderungen im Bereich Data & AI zu diskutieren.
Die Teilnahme ist kostenfrei. Die Plätze sind begrenzt.

Register for free here: https://pirateskills.com/events/vibe-coding-cologne/2026-11-04

Ready to turn your next big idea into a working product before the pizza gets cold? Vibe Coding Cologne is a high-energy evening where founders, product managers, marketers and developers learn to ship with AI-assisted speed.

Why join?
* Go from zero → MVP in hours. Spin up prototypes, landing pages and automations without hunting for a technical co-founder.
* Let AI handle the grunt work. Bug fixes, tests, docs and campaign personalisation run on autopilot, so you can stay in your creative zone.
* Real-world demos, not fluff. Watch live builds of customer-support bots, AI-powered marketing funnels and more — then try the tools yourself during networking.

Who’s it for?
* Founders cutting the cost and time to validate ideas.
* Product managers testing features with stakeholders today, not next sprint.
* Marketers launching personalised funnels at hyperspeed.
* Developers automating the boring stuff to focus on impact.

• What’s happening?
• 18:30 - Arrival and Networking
• 19:00 - Welcome & Intro by Ben
• 19:15 - Talks around Vibe Coding and AI by guests
• 20:30 - Drinks & networking with fellow vibe-coders

When & Where
November 4th, 18:30 - 21:00, STARTPLATZ Cologne
Im Mediapark 5, 1st Floor, Room: Barcelona
Capacity is capped at 100, so grab your free seat now.

💻 Can't make it to Cologne? Join online: https://us02web.zoom.us/j/85025002365

https://pirateskills.com/events/vibe-coding-cologne/2026-11-04