Write Playwright tests with Playwright MCP and Claude Code
A walkthrough of using Playwright MCP with Claude Code to generate Playwright tests in minutes.
Done withClaude Code
- What they did
- The Playwright MCP server is registered with Claude Code, loaded with a saved logged-in session through storage state. A three-part prompt carries the environment facts, a plain-English scenario, and standing rules. The agent explores the live app through the accessibility tree, writes the test, runs it, and fixes failures itself. A person reviews the code and the scenario's meaning.
- How it went
- The agent produced a runnable test with locators read from the live page. It also fixed a strict-mode locator error on its own. It struggles with long flows, changing data, deep conditionals, and OAuth. The source gives no timing numbers.
- Worth knowing
- Add .auth/ to .gitignore before committing, because this setup saves the session outside Playwright's default ignored path, and run the test with --repeat-each 5 to check for flakiness.
Try it yourself with Claude Code
Set up Playwright MCP in this project, then open [app URL] and explore the flow for [user journey, e.g. sign up and checkout]. Write Playwright tests that cover it using stable locators, and run them until they pass. Finish by showing me the test files and the passing run output.
Source: DEV · Oct 5, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Run content research and sponsor outreach with Claude computer use
The author tested Claude computer use in Cowork and Claude Code over two days on six workflows including research, sponsor outreach and product listings.
Build and balance a live Telegram RPG
A non-coding PM had Claude Code write a Telegram RPG bot, deploy it over SSH, and run tens of thousands of test fights to rebalance classes.
- Claude
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Build and test a simple endpoint project with Devin
A reviewer had Devin set up a project, write code, install dependencies, test endpoints and add error handling in about 4 minutes on a simple task.
Build a booking and payment app for tattoo artists
A former programmer used Replit Agent over a weekend to build a booking app with calendar, Google OAuth, Stripe deposits and notifications, though time zones and UI needed back-and-forth.