Automation of the Automation using ChatGPT
summary
Walks through generating Playwright + TypeScript API tests with ChatGPT (stable GPT‑3.5) via Postman/API, saving generated files to a GitHub GPT branch, executing them as child processes, capturing execution logs and tokens, and implementing retry logic and a simple self‑healing loop that asks GPT to fix failing tests. Demonstrates that one broken GET test needs about 7 iterative prompts to pass, timeouts and token costs occur, and occasional third‑run success proves the approach but not full reliability.
AI-written summary · about
chapters (11)
- 0:00Automation with ChatGPT
- 1:03QA engineer tasks overview
- 5:41QA tasks for AI automation
- 6:03Prompt engineering basics
- 9:18Prompt engineering tips
- 17:01Testing framework with ChatGPT
- 21:05Demo: API tests with Playwright
- 32:52ChatGPT API integration
- 45:56Self-healing tests
- 1:06:29Future framework enhancements
- 1:11:23Q&A
related talks
01h 26mAutomation of the Automation using GenAI
48mTestGPT: Generative AI (AutoGPT, ChatGPT & VisualGPT)
01h 12mHow ChatGPT can make you a better Software Developer
51mTDD with ChatGPT
31mGetting the most out of Chat GPT
24mWriting Tailormade Unit Tests with ChatGPT
39mHow ChatGPT helps to boost your development efficiency
27mChatGPT Ignites