Agentic Testing: Your Skilled Human Tester
summary
Agentic testing uses LLMs (Gemini, GPT) plus tools like Playwright MCP, Postman agents and Mabel to run goal‑driven, multi‑agent tests that observe DOM and video, reason, adapt and auto‑heal. Examples: an autonomous exploratory agent finds a console error, captures screenshots/DOM/network and files a full bug report; a diff‑driven agent generates a risk‑based test plan and reduces a 2‑hour regression to 2 minutes; agents use vector DB + RAG for memory and auto‑triage into Jira/Slack.
AI-written summary · about
chapters (26)
- 0:00Agentic testing introduction
- 2:12Modern QA automation challenges
- 5:27What is agentic testing
- 7:58Three AI testing evolution levels
- 10:09AI agents perceive and act
- 12:38Orchestrating multi-agent teams
- 14:02Autonomous exploratory testing
- 16:13Dynamic test strategy generation
- 17:59Breakthrough AI testing capabilities
- 19:05MCP frameworks for agentic ecosystems
- 20:57AI test workflow examples
- 25:35Playwright MCP for test generation
- 26:58Human-like AI testing tools
- 28:47AI agents in CI/CD pipelines
- 29:10Challenges in agentic testing
- 30:38Self-adapting test suites
- 31:43LLM for advanced assertions
- 32:48Impact on QA roles
- 34:54AI test strategies over scripting
- 35:58Summary and future of agentic testing
- 37:24Q&A on AI testing
- 38:06When to implement AI details
- 39:32Can AI replicate QA intuition
- 41:22ROI of AI in testing
- 43:59Technical AI trade-offs
- 46:05Closing remarks
related talks
18mReinventing App Testing with Agentic Apps
30mAgentic QA vs LLM Dev: A Live AI Showdown in the DevOps Arena
43mTesting Agentic AI Applications: Beyond Traditional QA
14mAutonomous Testing Agents with LLMs in React
48mSupercharged Testing: AI-Powered Workflows with Playwright + MCP
31mTesting, Evaluating and Debugging Generative AI and Agentic Ap...
35mThe Agentic AI Engineer
37mAI agents testing How to evaluate the unpredictable