Surviving and Thriving with AI in QA
summary
Cuts the AI hype with specific limits and tactics: warns of model collapse and LLMs lacking spatial understanding and determinism, shows a working custom OpenAI API log-sifting tool that finds anomalies, recommends starting with low‑risk, high‑reward pilots, defining clear objectives like reduce escape defects by 10% per year, treating AI output like junior code with code reviews, keeping manual exploratory testing, and making QA of AI part of the process.
AI-written summary · about
chapters (14)
- 0:00AI in QA introduction
- 1:53AI as teammate in QA
- 4:02AI flaws in testing
- 7:39AI impact on testing communities
- 12:45AI adoption challenges in QA
- 17:36Ethics of AI in testing
- 22:19Integrating AI in testing
- 26:17Future of human-AI QA
- 28:03Q&A: AI testing adaptation
- 30:34Q&A: Mentoring with AI tools
- 32:26Q&A: Traditional vs AI testing
- 34:14Q&A: AI workflow challenges
- 37:33Q&A: Advice for junior QAs
- 40:09Closing remarks
related talks
32mQuality engineering in the AI age: From testing AI to leveraging GenAI
55mSurviving the AI Testing Apocalypse
31mThe Copilot Wrote It but Who Saves It: Surviving the AI Code Tsunami
22mBeyond Bugs: How AI turns QA into Full-Circle Engineers
15mPractical tactics to build reliable AI apps
29mTesting for Ghosts in the Machine: Assuring 'Good Enough' Software Quality in AI-based systems
27mHow to Build AI Agents and Keep Your Sanity
30mAgentic QA vs LLM Dev: A Live AI Showdown in the DevOps Arena