Impact of AI on #SoftwareTesting: Are Testers Ready? 🔮
summary
Panelists describe concrete wins: a dedicated squad trains LLMs on e‑commerce and historical test data to spin up brand-specific test boilerplate one‑click environments, generate traffic models from Postman/Swagger, and output Gatling scripts that estimate infra needs (example target 2,000 TPS with 10% conversion and P90 <50ms). They report six months of production experiments, warn to host private LLMs for sensitive data, and list tools used like GitHub Copilot, Replit/Replicate, and relics for visual path generation.
AI-written summary · about
chapters (11)
- 0:00Introduction and panel setup
- 4:08AI in testing use cases
- 11:38AI for performance testing
- 22:39AI in software delivery
- 25:28Future of tester roles
- 33:43Merging technical and non-technical roles
- 40:30Getting started with AI
- 42:16AI risks and ethics
- 50:46Security with AI tools
- 56:02Common AI tools in testing
- 1:03:51Closing remarks and Q&A
related talks
46mThe Real Impact of AI in Software Testing
44mHow AI is Exposing the Existential Crisis of Software Testing
01h 05mPanel Discussion - The Future of Testing: Impact of AI in Quality Assurance and Beyond
44mPanel Discussion | The AI Revolution in Testing: Opportunities and Challenges
41mHow AI is transforming software testing
43mAI for Testing – Panel Discussion
14mPrompt Engineering Impacts to Software Testers : Staying in Demand
44mAI Empowered Software Testing