WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe - Virtual Stage • Jul 1, 2026 • Session details

MAD About Software Design - When AI Architects Argue

Lior Schejter

Why rely on a single, hallucination-prone AI for software architecture? Discover how multi-agent debates pit specialized AI personas against each other to autonomously design and refine complex systems.

Pause
Mute Enter Fullscreen
#1 about 4 min

Moving beyond coding assistants to software system design

Addressing software engineering bottlenecks requires applying artificial intelligence to complex system architecture rather than just code generation.

#2 about 2 min

Challenges with prompt-based AI system design queries

Single-prompt interactions often fail for system design due to model hallucination, overconfidence, and early anchoring.

#3 about 2 min

Human team collaboration as a model for AI architecture

Structuring artificial intelligence interactions like human team discussions enables multiple perspectives to evaluate trade-offs and reach architectural convergence.

#4 about 2 min

The multi-agent debate pattern for autonomous technical decisions

Letting large language models critique and refine each other's proposals creates an autonomous mechanism for reaching cohesive architectural decisions.

#5 about 2 min

Defining agent personas, topology, and debate convergence mechanisms

Effective debate architectures require specific agent roles, defined communication pathways, and clear criteria for concluding discussions.

#6 about 2 min

Solving contradictory design constraints through adversarial AI debate

Adversarial pressure between agents forces models to highlight implicit assumptions and balance competing technical constraints.

#7 about 2 min

Automating architectural discussions using the Dialectic command tool

The Dialectic tool introduces specialized expert personas to propose, critique, and synthesize architectural drafts autonomously.

#8 about 3 min

Configuring agent debates and answering clarifying system questions

Allowing models to ask clarifying questions about user requirements dramatically improves the final system architecture.

#9 about 4 min

Evaluating AI debate quality against formal architecture katas

Systematic testing reveals that clarifications improve results while summarization and excessive debate rounds degrade design quality.

#10 about 3 min

Controlling design outcomes by adjusting specific agent personas

Adjusting the number of specialized advocates in a debate predictably shifts the resulting architecture toward desired qualities.

#11 about 4 min

Deploying debate skills on autonomous agentic coding platforms

Executing debate protocols within environments like Claude Code or Cursor streamlines integration but increases raw token consumption.

#12 about 4 min

Integrating debates into an autonomous software development lifecycle

Connecting automated architectural debates with coding agents and continuous deployment pipelines points toward fully autonomous system evolution.

#13 about 3 min

Applying multi-agent AI debate to everyday engineering workflows

Using multi-agent systems as automated private consultants helps engineers pressure-test drafts and uncover missing system considerations.

Matching moments

2:54 min

Designing complex software architecture in the era of AI

Chris Heilmann +2 · LIVE

2:02 min

Redefining the software architect role for AI pipelines

Ingo Eichhorst Ingo Eichhorst · World Congress 2026 Europe

2:34 min

Balancing developer autonomy with the adoption of coding agents

Clemens Wasner Clemens Wasner +4 · World Congress 2026 Europe

2:06 min

Rethinking team structures around AI agent capabilities

Mike Mike · World Congress 2025

1:32 min

Architectural patterns for developing robust generative AI applications

Julián Duque Julián Duque · World Congress 2025

10:17 min

Discussion on AI hallucinations and practical developer workflows

Akmal Chaudhri Akmal Chaudhri · LIVE

More from World Congress 2026 Europe - Virtual Stage

One Does Not Simply Make Architecture Decisions Alone thumbnail
36:15
2 months ago

One Does Not Simply Make Architecture Decisions Alone

Vladas Diržys

From Black Box to Glass Box : Bedrock AgentCore Observability thumbnail
21:15
2 months ago

From Black Box to Glass Box : Bedrock AgentCore Observability

Yasemin Aktürk

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence thumbnail
30:41
2 months ago

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence

Julia Grosse

Better Together: Leveraging Your Observability Tools as a SIEM thumbnail
39:06
2 months ago

Better Together: Leveraging Your Observability Tools as a SIEM

Mathias Palmersheim

ChatGPT Apps: From Chat to Checkout thumbnail
30:29
2 months ago

ChatGPT Apps: From Chat to Checkout

Aaron Koivunen

Interior Decorating (TypeScript Decorators) thumbnail
29:22
2 months ago

Interior Decorating (TypeScript Decorators)

Michael Dowden

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 15:10–15:20

Outdoor Stage

AI That Argues With Itself: Building Self-Debating Systems That Catch Their Own Bugs

Shreya Singhal

AI Applied Scientist at Claritev

Shreya Singhal
Open session

World Congress 2026 North America

September 24, 2026 · 13:30–15:30

Stage 13

RoboCoders: Judgment Day: AI-Assisted Engineering Applied - The Battle of Agents

Baruch Sadogursky, Viktor Gamov

Baruch Sadogursky
Viktor Gamov
Open session

World Congress 2026 North America

September 24, 2026 · 12:15–12:45

Stage 4

It's Not About the Models

Bob Wambach

Vice President, Market and Customer Insights for Dynatrace

Bob Wambach
Open session

World Congress 2026 North America

September 24, 2026 · 16:50–17:20

Mainstage

Building AI Products vs. Building With AI

Aparna Dhinakaran, Rukmini Reddy, Tamar Bercovici

Aparna Dhinakaran
Rukmini Reddy
Tamar Bercovici
Open session

World Congress 2026 North America

September 24, 2026 · 11:10–11:15

Outdoor Stage

Architecting the 100X SDLC: Building Production Trust into AI-Assisted Delivery

Ranjan Parthasarathy

Founder, CPTO/CEO at AXIOMSTUDIO.AI

Ranjan Parthasarathy
Open session

World Congress 2026 North America

September 23, 2026 · 13:15–15:15

Stage 9

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal

Related videos

AI Killed DevOps... What Now? - Lee Faus thumbnail
57:43
Coffee With Developers • 10 months ago

AI Killed DevOps... What Now? - Lee Faus

Lee Faus

25 Years After Agile, And Yet We're Building Waterfall Agents - Martin Hynie thumbnail
36:56
Coffee With Developers • 4 months ago

25 Years After Agile, And Yet We're Building Waterfall Agents - Martin Hynie

Martin Hynie

Designing high quality software with AI thumbnail
30:46
World Congress 2026 Europe • 2 months ago

Designing high quality software with AI

Brian Lovin

Best Practices for AI-Assisted Development of Distributed Systems thumbnail
28:07
World Congress 2026 Europe • 2 months ago

Best Practices for AI-Assisted Development of Distributed Systems

Przemysław Ładyński

One Does Not Simply Make Architecture Decisions Alone thumbnail
36:15
Europe 2026 Virtual • 2 months ago

One Does Not Simply Make Architecture Decisions Alone

Vladas Diržys

The AI-Native Engineering Org: What’s Real, What’s Hype, What’s Next thumbnail
28:33
World Congress 2026 Europe • 2 months ago

The AI-Native Engineering Org: What’s Real, What’s Hype, What’s Next

Taroon Mandhana, Sebastian Kister

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.