Engineering systems in the AI shift

Doors open, registration, drinks & snacks

AI-native architecture

Two teams can deploy the exact same model and walk away with completely different results. The model isn’t the differentiator. The system is.

Agentic AI forces teams to externalize reasoning, formalize decisions, and design for traceability.

At scale, modern product development needs AI-native architectural practices: evolvable contexts, collaboration between human and AI agents, and reliable governance.

At a point where AI is able to replicate the engineering reasoning of top architects, this session shares a view on what may be the next evolutionary step for engineering discipline — an AI-Native Architecture Capability.

Break — catered food, drinks, networking

Moderated discussion: AI shift (risk, responsibility, adoption)

In groups of 6–8, participants will talk about the practical tensions of integrating AI into their engineering systems:

• irreversible architectural decisions
• hidden long-term risks
• team skepticism & adoption strategies
• standardization vs experimentation

The format is designed to speak openly, compare approaches, and challenge assumptions with peers operating at a similar level of responsibility.

Break — catered food, drinks, networking

AI agents as operating systems

Modern agents increasingly resemble operating systems in how they coordinate context, tools, memory, and constraints.

Using a real production agent as an example, this session explores:

• structural parallels to operating systems
• what’s genuinely new (self-evolution, identity persistence, embedded ethical boundaries)
• how to reason about agents as infrastructure rather than features

A practical framework for teams building agentic systems beyond prototypes.

Networking & afterparty

More time to connect over food and drinks.

Talk to peers and get more clarity on how to design AI-native systems, or at least learn how others are doing it.

‍

‍