World Congress 2026 Europe Jul 9, 2026 Session details

Beyond LLM Agents: A World Model for Visual Software Testing

Manuel Weichselbaum

Real-world software testing demands deterministic results, not fragile LLM agents. Discover how a lightweight visual world model securely automates UI tests on standard CPUs without prompt vulnerabilities.

Pause
Mute Enter Fullscreen
#1 about 1 min

Limitations of current performance benchmarks for agentic AI

Shifting the evaluation goalpost from single-task execution to reliable, repeatable automation reveals weaknesses in saturated performance benchmarks.

#2 about 1 min

Challenges of grindable parallel rollouts in UI testing

Executing thousands of AI interactions against real-world webpages requires grindable systems rather than just verifiable actions.

#3 about 1 min

Abstracting UI interactions for secure and automated execution

Mapping a core concept library of abstracted behavior prevents prompt injections while reducing computing overhead.

#4 about 2 min

Vision action model architecture for visual software testing

Utilizing simple visual targets and sigmoid activation creates reliable confidence signals for autonomous bug detection.

#5 about 1 min

Comparing model scale and operational computation costs

Deploying a specialized vision model at a fraction of typical sizes retains benchmark compatibility while reducing infrastructure costs.

Matching moments

3:30 min

Applying visual language models for automated self-healing tests

Daniel Afonso Daniel Afonso · World Congress 2025

5:27 min

Evaluating AI agents through unpredictable behavior and logic tests

Chris Heilmann +2 · LIVE

3:46 min

Integrating AI into web performance engineering workflows

Perf + AI

1:21 min

Handling screen reader simulations using AI agents

Jörg Jakoby Jörg Jakoby · World Congress 2026 Europe

50 sec

Introduction to AskUI and vision agent capabilities

Jonas Menesklou Jonas Menesklou · World Congress 2025

2:20 min

Validating user experiences directly with automated QA agents

Ohans Emmanuel Ohans Emmanuel · World Congress 2026 Europe

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 25, 2026 · 15:45–15:55

Outdoor Stage

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Frontier AI Lead at Turing

Vivek Pandit
Open session

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 6

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

September 24, 2026 · 11:20–11:25

Outdoor Stage

Finding the Edges: Testing, Evaluating, and Monitoring Voice AI Agents Before Your Users Do

Matt Wyman

CEO at Okareo

Matt Wyman
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 2

Reinventing Testing Practices in the AI Era

Eric Deandrea

Java Champion & Senior Principal Software Engineer, IBM

Eric Deandrea
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 24, 2026 · 09:45–10:15

Mainstage

Manufacturing trust: speed and safety in the age of agents

Mark Cavage

Mark Cavage President and COO of Docker

Mark Cavage