Alexander Gyulai: A Practical Guide to Transforming Quality Assurance with Intelligent Solutions
summary
Auto1 Group runs 900 microservices with about 400 deployments per week and 12,000 tests a day; the team builds small AI services that search test data with natural language, extract unreadable error logs into structured JSON via a Longchain-based pipeline, fetch related GitHub classes and return file-level pointers, and iterate prompts (often 100+ tries) and system messages to tune outcomes. The test-data search and error-analysis tooling works well; automated test-case generation requires multi-step context slicing (128k context, ~4k completion) and many iterations to reach acceptable quality.
AI-written summary · about
chapters (10)
- 0:00AI in QA introduction
- 5:12AI for QA assessment
- 9:07Prompt engineering basics
- 13:23Multimodal AI and system messages
- 17:23Practical AI use cases in QA
- 19:57Test data generation with AI
- 22:51Debugging test failures with AI
- 27:06AI-assisted test case creation
- 32:47AI adoption challenges in QA
- 36:42Q&A
related talks
42mIt's Inevitable, Mr. Anderson: Machines, Humans, and the Future of Testing
46mQA to QE: Scaling Quality with Ownership, Code, and Culture
47mPanel Discussion: Who Tests the Machines? QE Leaders on Quality in the Age of AI-Written Code
31mScaling Quality in a Decision Intelligence Platform: The Agentic QA Playbook
43mLean QA: Automation, Monitoring, Experiments
22mLeveraging Quality Intelligence and AI to Improve the Quality of Java Applications
42mThe Power of Human and AI Collaboration in Software Testing
22mBeyond Bugs: How AI turns QA into Full-Circle Engineers