WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 9, 2026 • Session details

Your Distributed System Just Got a Brain. Now What?

Marcin Makowski

Treating AI as a predictable microservice will inevitably collapse your distributed systems. Discover why engineering teams must never deploy an artificial brain without a deterministic nervous system.

Pause
Mute Enter Fullscreen
#1 about 2 min

Integrating probabilistic AI into distributed systems

Adding artificial intelligence introduces probabilistic dependencies that challenge traditional deterministic architectures.

#2 about 3 min

Why probabilistic models break retry semantics

Large language models generate varying outputs for identical inputs, turning standard retries into unpredictable business decisions.

#3 about 1 min

Separating AI inference from business state mutations

AI outputs should serve as proposals bounded by explicit business rules rather than direct state changes.

#4 about 2 min

Establishing deterministic checkpoints in AI workflows

Systems must freeze model versions, prompts, and contexts to guarantee repeatable execution paths and stable explanations.

#5 about 2 min

Translating unstructured documents into executable business logic

Artificial intelligence can automatically extract facts and propose execution rules using formal decision and process models.

#6 about 2 min

Enforcing human-in-the-loop governance for AI-generated models

AI-generated logic requires explicit review, testing, and approval by humans before moving into production runtimes.

#7 about 3 min

Designing open modeling environments for hybrid architectures

Connecting open building blocks establishes a model-driven layer that functions alongside traditional engineering constraints.

#8 about 2 min

Managing enterprise execution with the Operate runtime

An open execution layer translates approved workflows and generated decisions into durable, auditable business logic.

#9 about 2 min

Embedding the Java runtime in developer environments

Developers can configure the execution layer natively within common containerized or Java-based frameworks.

#10 about 2 min

Governing enterprise logic in an AI-driven landscape

Sustaining an intelligent system requires that generated logic remains validated, executable, and fully auditable by humans.

Matching moments

3:05 min

Differentiating artificial intelligence systems from classical deterministic software

Nikita Golovko Nikita Golovko · Europe 2026 Virtual

2:02 min

Redefining the software architect role for AI pipelines

Ingo Eichhorst Ingo Eichhorst · World Congress 2026 Europe

3:34 min

Architecting autonomous agents for production lifecycle management

Sebastian Kister Sebastian Kister · World Congress 2026 Europe

1:29 min

Overcoming challenges in AI-assisted distributed system development

Przemysław Ładyński Przemysław Ładyński · World Congress 2026 Europe

3:08 min

Managing the impact of AI on software trust

Serge Baumberger Serge Baumberger · Europe 2026 Virtual

1:30 min

Transitioning from machine learning models to complex agentic systems

Alejandro Saucedo Alejandro Saucedo · World Congress 2025

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

You are not an AI developer thumbnail
23:55
World Congress 2024 • about 2 years ago

You are not an AI developer

Zan Markan

AI for Enterprise Developers - Dr. Damir Dobric thumbnail
32:55
Coffee With Developers • 7 months ago

AI for Enterprise Developers - Dr. Damir Dobric

Damir Dobric

Running AI at Scale: The Secret Ingredients thumbnail
30:04
World Congress 2026 Europe • 3 months ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

Best Practices for AI-Assisted Development of Distributed Systems thumbnail
28:07
World Congress 2026 Europe • 3 months ago

Best Practices for AI-Assisted Development of Distributed Systems

Przemysław Ładyński

The Limits of LLMs in Real-World Applications thumbnail
31:07
World Congress 2026 Europe • 3 months ago

The Limits of LLMs in Real-World Applications

Deivids Vilkinsons, Guillaume Esnou, Laura Moritz, Mariam Hakobyan

Architecture 3.0: From 90% to 99.999% Reliability in Building AI Systems thumbnail
31:16
World Congress 2026 Europe • 3 months ago

Architecture 3.0: From 90% to 99.999% Reliability in Building AI Systems

Ingo Eichhorst

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.