New AI Features in Playwright (Live-Webinar)

An AI agent that can't open a browser is just guessing. Stefan from Checkly shows how giving AI coding agents a real browser via Playwright enables reliable end-to-end test generation and debugging, closing the quality gap created by faster, AI-driven shipping.

The session compares Playwright MCP vs the Playwright CLI for agent workflows, showing that thanks to MCP spec changes, lazy tool loading, and skills, the two are now effectively just different interfaces to the same tool, with no real token advantage either way.

Stefan demos fixing a failing test using error context, the new text-based trace tooling, and CLI-driven debugging, then shows annotations and screencast video creation as proof of work.

He also discusses Playwright's built-in agents, converts the generated test into a Checkly production monitor, and demonstrates Checkly's Rocky AI root-cause analysis accessible via the CLI.

00:00 Welcome and Agenda

01:00 Checkly and the Quality Gap

04:03 Why Agents Need Browsers

05:07 Playwright AI Snapshots

07:07 MCP vs CLI Token Reality

16:02 Generating a Test Live

19:50 Fixing Failures with Traces

24:58 CLI Debug Attach Workflow

27:40 Annotations and Screencasts

37:10 Playwright Built-In Agents

39:56 From Tests to Checkly Monitors

44:09 Rocky AI and Closing Thoughts

#checkly #playwright