Ensuring Quality Testing in an AI-driven World
summary
Demo shows a real repo (Mish Friendly Food) getting a new export feature with four card styles, implemented and iterated by GitHub Copilot agent mode, which edits files, runs Playwright tests and reports 33 additions then fixes failing tests until all nine E2E tests pass. Presenter cites productivity numbers (GitHub Copilot 88% better review outcomes, 46% productivity uplift reported, Atlassian saves 105 minutes/day) and argues humans must remain auditors for ethics, empathy and bias.
AI-written summary · about
chapters (10)
- 0:00Welcome to AI-driven testing
- 3:11Software testing evolution
- 7:45Why test software matters
- 9:56Testing history and AI's role
- 13:46GitHub Copilot testing demo
- 22:16AI productivity and concerns
- 24:47GitHub Copilot agent demo
- 32:56AI versus human testing skills
- 40:46Future of software testing
- 43:17Q&A on AI quality
related talks
33mEnsuring quality in an AI-driven world
16mShift Left with GitHub Copilot: Enforcing Code Quality Before the Commit
50mPanel: Beyond The Vibe: Code Quality First
24mGitHub Copilot Agents + Sonar | The Blueprint for Agentic Development
40mUnlocking Productivity with GitHub Copilot Best Practices and Tips
53mImprove Your Code Quality and Performance using AI and GitHub Copilot
45mThe AI Revolution in Software Development: From Code Writing to Quality Assurance
16mTackling tech debt