Panel Discussion | The AI Revolution in Testing: Opportunities and Challenges
summary
Panelists describe concrete wins and constraints: a pilot that boosts ad revenue, a log‑analysis model that flags anomalies before incidents, and a Chrome extension prototype that captures screenshots and builds docs in hours but required security gating. They run graph‑based RAG (Neo4j + Chroma-like vectors) and local LLMs such as Claude or Mistral via llm Studio, use Cursor and Diffblue for code and tests, and experiment with large action models that automate UI tasks; EU AI Act and data air‑gaps dictate deployment choices.
AI-written summary · about
chapters (9)
- 0:00Welcome
- 6:50AI in regulated industries
- 14:59Starting with AI in testing
- 19:21AI productivity use cases
- 26:49Time savings in QA
- 31:52Trustworthy AI systems
- 37:31Future of AI in testing
- 42:09AI amplifies human skills
- 43:58Closing
related talks
50mPanel Discussion: What Can Go Wrong With AI in Testing?
01h 05mPanel Discussion: Building Confidence in AI-Driven Testing Decisions
01h 04mImpact of AI on #SoftwareTesting: Are Testers Ready? 🔮
01h 05mPanel Discussion - The Future of Testing: Impact of AI in Quality Assurance and Beyond
28mXtremeJS Xperts Panel: The AI Revolution in Coding – Tools, Trends, and Tomorrow
40mPannel Discussion | From Hype To Value: Real World Applications Of Generative AI And LLMs
47mPanel Discussion: QE Strategic Shift: What's Changing with AI, Automation, and Speed?
41mPanel discussion: AI in code development – hype vs reality