WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Best Practices for AI-Assisted Development of Distributed Systems

Przemysław Ładyński

AI coding tools default to generic architectures for distributed systems. Stop software typing and master engineering coordination by encoding strict architectural rules directly into your codebase.

Pause
Mute Enter Fullscreen
#1 about 2 min

Overcoming challenges in AI-assisted distributed system development

Generating complex distributed systems requires providing AI with explicit architectural guidance rather than relying on basic prompts.

#2 about 2 min

Adapting the software engineering role for AI collaboration

As AI coding usage increases, engineers must transition from writing code to coordinating and supervising intelligent agents.

#3 about 2 min

Preventing generalized code outputs relying on internet averages

Without strict architectural guidance, AI defaults to generating average, unstructured code based on generalized training patterns.

#4 about 1 min

Defining repository boundaries using policies, skills, and specs

Supplying explicit rules and technical definitions within a codebase ensures AI correctly follows existing architectural constraints.

#5 about 4 min

Validating code generation with evals, datasets, and graders

Constructing repeatable regression tests for AI guarantees that agent-generated workflows meet organizational standards during pull requests.

#6 about 2 min

Delegating development tasks through progressive levels of autonomy

Workflows to process engineering tasks range from basic prompting to fully autonomous agents executing continuous integration checks in cloud environments.

#7 about 1 min

Steering statistical machine learning models toward custom architectures

Treating AI as an automated team requires mapping deep programmatic strategy into actionable repository parameters to avoid hallucinated infrastructure.

#8 about 2 min

Applying structural rules to restrict standard project generation

Embedding strict coding rules curtails unwanted dependencies and forces code generation pipelines to align with secure, predefined technical boundaries.

#9 about 4 min

Orchestrating tool skills for diagrams and structured features

Providing models with specialized tooling ensures architecture diagrams and markdown documentation are accurately generated and synced with internal files.

#10 about 7 min

Selecting optimized toolchains to improve context token efficiency

Selecting frameworks that utilize minimal boilerplate immediately lowers AI operational costs and reserves the restricted prompt context window.

#11 about 3 min

Competing fundamentally through proficient AI orchestration and coordination

Maintaining continuous operational advantages involves meticulously minimizing generative waste to rapidly output precise, scalable cloud infrastructure.

#12 about 3 min

Navigating over-formalization and repository context window thresholds

Grouping microservices into unified monorepos grants intelligent assistants superior programmatic context but requires careful boundaries to prevent excessive codebase scanning and token exhaustion.

Matching moments

2:54 min

Designing complex software architecture in the era of AI

Chris Heilmann Chris Heilmann +2 · LIVE

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann Chris Heilmann +2 · LIVE

4:24 min

Navigating accountability and architecture in AI generated code

Lilia Gargouri Lilia Gargouri · Coffee With Developers

2:06 min

Rethinking team structures around AI agent capabilities

Mike Mike · World Congress 2025

3:55 min

Moving beyond coding assistants to software system design

Lior Schejter Lior Schejter · Europe 2026 Virtual

2:47 min

Applying architectural frameworks to AI development constraints

Matheus Guimaraes Matheus Guimaraes · World Congress 2026 Europe

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

Building the next generation of AI developer tools thumbnail
30:34
World Congress 2026 Europe • 3 months ago

Building the next generation of AI developer tools

Krzysztof Cieślak

The AI-Native Software Team: How Agents Are Rewriting the SDLC thumbnail
31:13
World Congress 2026 Europe • 3 months ago

The AI-Native Software Team: How Agents Are Rewriting the SDLC

Marcin Wawryszczuk

Why optimizing for system comprehension is key to implementing AI for software development thumbnail
22:22
World Congress 2026 Europe • 3 months ago

Why optimizing for system comprehension is key to implementing AI for software development

Peter Caron

Developer Productivity Using AI Tools and Services - Ryan J Salva thumbnail
59:16
Coffee With Developers • over 1 year ago

Developer Productivity Using AI Tools and Services - Ryan J Salva

Ryan J Salva

Developers become Orchestrators: From Human-in-the-Loop to Spec-in-the-Loop thumbnail
30:01
World Congress 2026 Europe • 3 months ago

Developers become Orchestrators: From Human-in-the-Loop to Spec-in-the-Loop

Bastian Heilemann, Stefan Bley

Building and Modernising Apps with Agentic AI - Julia Kordick thumbnail
38:01
Coffee With Developers • 7 months ago

Building and Modernising Apps with Agentic AI - Julia Kordick

Julia Kordick

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.