LLM-Powered Automation for Scalable UI Testing | Ai Heroes 2024 Talk скачать в хорошем качестве

LLM-Powered Automation for Scalable UI Testing | Ai Heroes 2024 Talk

Automated UI testing is essential but notoriously fragile, often failing to keep pace with rapidly evolving interfaces and documentation. In this talk, we introduce a novel multi-agent architecture that leverages large language models (LLMs) to transform static documentation into dynamic, executable UI tests—without writing code. Our system extracts structured user journeys from product manuals, refines them into atomic tasks using LLM agents, and executes them autonomously in live browser environments. This talk is for developers, QA engineers, and AI practitioners building or maintaining test automation pipelines in enterprise environment. Attendees will gain insights into architecting LLM-powered agents for structured extraction, and improving test resilience. We'll explore how this system achieves high execution accuracy and adaptive self-correction, even under ambiguous or incomplete specs. 🎤 MICHELANTONIO TRIZIO, Chief Technology Officer 🎤 ANDREA LOPS, Ph.D. Student & ML Engineer ⏩ Chapter: 00:00 Intro 02:14 Software Testing Hierarchy 06:40 Limits 08:51 LLM applied to testing 14:27 Developing Our Solution 15:18 First iteration 16:32 Pro & limits 17:55 Second iteration 22:04 Third iteration 25:18 Dynamic retry 27:09 Fourth iteration 29:26 New agents 30:44 Fifth iteration 32:20 Final result 34:19 Usability considerations 35:15 A new way for UI testing 📍AI Heroes is the Italian Artificial Intelligence Conference for Developers, Engineers, Data Scientists & Product Managers. The New Workflow to Shape the Future of Business AI in the Next Generation Workforce Key Technologies, Applications and Trends ℹ️ inform: https://aiheroes.it/ ✅ Tweet:   / aiheroes_it   ✅ Connect:   / aiheroes-it   ✅ Read: https://t.me/aiheroes #AIHeroes2025 #LLMTesting #UIAutomation #TestAutomation #QAEngineering #LargeLanguageModels #AITestingTools #ScalableAutomation #ZeroCodeTesting #AutonomousAgents