It's Inevitable, Mr. Anderson: Machines, Humans, and the Future of Testing
summary
Auto1 Group deploys about 15,000 changes a year across ~900 services and uses five AI agents that four QA engineers build to augment testing workflows. Agents range from coding agents (Cloud Code, GitHub Copilot etc.) to a Slack runner; results include 80% of test cases created by AI with no measurable regressions, ~8,000 total tests, 50–100 weekly maintenance failures, about 70% of AI PRs merged, fixes costing roughly $0.25 each, and ~300 Slack-triggered runs per month.
AI-written summary · about
chapters (11)
- 0:00Future of testing
- 1:07AI agents in engineering
- 3:35AI agents vs LLMs
- 8:12AI agents transforming QA
- 11:27Automated test planning
- 17:05Test maintenance automation
- 24:39Chat for system testing
- 28:54Slack test results bot
- 31:03Future of AI in testing
- 33:11Adopting AI tools
- 35:15Q&A
related talks
47mPanel Discussion: Who Tests the Machines? QE Leaders on Quality in the Age of AI-Written Code
25mWhat’s Our Job When The Machines Do Testing?
22mBeyond Bugs: How AI turns QA into Full-Circle Engineers
41mHow AI is transforming software testing
26mAI Agents as Your Co-Developer
44mHow AI is Exposing the Existential Crisis of Software Testing
42mThe Power of Human and AI Collaboration in Software Testing
01h 04mImpact of AI on #SoftwareTesting: Are Testers Ready? 🔮