Workshop: Legacy vs Autonomous QA Arena - Surviving the AI Driven Quality Evolution

on YouTube ↗01h 15m

" summary

Claims that 58% of test failures come from timing and locator issues and that these consume 30–40% of QA budget drive the session: legacy Selenium still underpins 65% of suites while Playwright adoption grows 235% year‑over‑year, KAI authors tests from plain‑English prompts, and a live deploy shows an AI observation layer detect a broken locator and apply selector (28%), timing (30%) and runtime (8%) heals in seconds with human‑approval thresholds.

AI-written summary · about

" chapters (40)

1. 0:00Start
2. 0:07Workshop Opens - Legacy vs Autonomous QA Arena
3. 0:37Speaker Intro - Athresh Guruprakash, Senior Engineering Manager, Equifax
4. 1:42Every Test Green Last Night, Every Test Red This Morning
5. 4:15Spot the Flaky Test: Element Not Interactable Exception
6. 5:1758% of Failures Are Timing and Locator Issues, 40% of QA Budget Maintains Them
7. 5:47Selenium Is Still the Undisputed King
8. 6:19Playwright Growing 235% Year-Over-Year
9. 6:49Selenium Isn't Dying - It's Being Rescoped
10. 8:23Cucumber BDD and Where It Stands
11. 10:25A Plain English Prompt to a Resilient Test
12. 10:5689% of Enterprises Pilot GenAI - Only 37% Reach Production
13. 12:27What Actually Changed: Not the Tools, the Architecture
14. 13:59The Modern Architecture Wraps an Adaptive Layer Around It
15. 14:30Self-Healing: What It Actually Means
16. 15:35Three Layers of Healing: Selector, Timing, Runtime
17. 17:08Watching a Heal Happen Live
18. 18:43What Can an Agent Not Do That a Human Still Has To?
19. 20:52QA Roles Grew 17% Last Year vs 9% for Developers
20. 21:54Why Regression Testing Just Became Critical Again
21. 22:54From Script Owner to Quality Owner
22. 24:30Q&A: Migrating a Massive Page Object Model Without a Rewrite
23. 25:32Q&A: Replacement or Another Layer?
24. 27:03Q&A: What Still Makes Sense as Scripted Selenium
25. 29:06Q&A: Upskilling Paths and Resistance
26. 30:07Q&A: Shifting Autonomous Quality Into the IDE and PR
27. 32:08Q&A: From Writing Test Steps to Supervising Agents
28. 34:11Q&A: Stopping AI From Repeating Legacy QA's Weaknesses
29. 38:47Q&A: Hallucination in Practice
30. 40:20Why the Human Approval Gate Exists
31. 41:38Q&A: Confidence Thresholds for Self-Healing Actions
32. 43:11Go Slow Until the Agent Has Earned It
33. 44:49Q&A: Chaos Engineering, Pen Testing and Risk-Based Testing
34. 47:26The Live Poll Begins
35. 57:06Open Poll: Your Number One Blocker to AI-Driven QA
36. 58:37A Strong Regression Baseline Is the Prerequisite
37. 1:02:11Q&A: When an Agent Misunderstands a Legacy Business Rule
38. 1:04:23Q&A: False Positives in Self-Healing
39. 1:06:27Q&A: Legacy BDD Flow vs Agentic Flow, End-to-End
40. 1:10:03Poll Winners Announced

" related talks

• 17mStaying Ahead: The Future of QA LeadershipDavid Ingraham · TestFlix 2024
• 01h 05mPanel Discussion - The Future of Testing: Impact of AI in Quality Assurance and BeyondParveen Khan, Pricilla Bilavendran, Naveen Khunteta, Ibironke Yekinni, Steve Caprara, Mahathee Dandibhotla · Spartans Summit 2025
• 42mThe Power of Human and AI Collaboration in Software TestingAleksandra Psheborovskaia · TestCon Europe 2023
• 41mHow AI is transforming software testingRaj Subramanian · SeleniumConf Chicago 2018
• 32mKeynote: AI & GenAI in Quality Engineering: Crawl, Walk, RunSubba Ramaswamy · TestMu Conference 2025
• 49mDiscussion Panel: QA in the Last Decade - Past Lessons and Future VisionsAnton Angelov, Nikolay Stanoev, Aleksandar Karamfilov, Dimitar Topuzov · QA: Challenge Accepted 2024 - The Anniversary
• 40mEvolution of Testing Function & Industry TrendsNaman Kapoor · QonfX 2024
• 45mTOP 5 Modern Stereotypes in QA WorldAna Palchevska · TestCon Europe 2025