Playwright

“Rolling your own Playwright / Puppeteer cluster works until target sites deploy new JA4/TLS fingerprints”

“I've had some luck on the web app side if I use playwright or similar for the model to interact with but still far from efficient.”

“that kind of test tends to be brittle and annoying to write (I guess I don't have to write them anymore, but they are still brittle)”

“Building simple web-scraping scripts with nbb driving Playwright is so much faster than using any other stack”

“works better with how models are already trained on playwright to interact with browser”

“Really like this approach to keeping Playwright deterministic while still getting AI-assisted fixes via PRs”

“Once it tracks down the bugs - boom! You have an end to end test to add to your suite.”

“with a Playwright task which attempts to surface errors to the agent who introduced the previous code block”

“playwright provides a lot of benefits that we like in terms of being code - like auto-waiting, good syntax for a lot of operations”

“This beats writing playwrights which often break when a major UI update happens.”

“guardrails not only in textfiles but much more in executable code (linters, tests, dependency checks, playwright, ...)”

“Playwright tests are an absolute delight to read, write and maintain on properly accessible sites”

“Things that have helped me elsewhere: Playwright with page.wait_for_selector rather than networkidle”

“I just created a playwright cli skill in about 30 minutes and I've been using it for months.”

“Same playwright is phenomenal. You can also have the agent browse with MCP to figure out the workflow, then bang out a repeatable playwright script for it.”

“Ask it to take control of a browser using something like Playwright and use the UI itself like an end user would”

“what turned me off it was the likelihood anyone not already using Playwright would have to update their frontend”

“getting them to a state where they reliably pass has always been so much more finicky than it should be”

“Playwright seems to do fine at visual stuff? It takes screenshots and the model evaluates them. That's most of what I use Playwright for.”

“If you want something that mostly just works, Playwright is still the easiest default.”

“often the playwright skill will verify using DOM API instead of wasting tokens on screenshots”

“the project that my CC is working on now is a playwright clone that is not easily detectable”

“I've also had Claude run javascript code on a page using playwright-cli to figure out why a button wasn't working as it should.”

“I give agent either a simple browser or Playwright access to proper browsers to do this. It works quite well”

“duct-taping browser automation (Playwright, CDP, MCP wrappers) onto an interface designed for humans”

“Getting them to take screenshots with playwright/puppeteer and look at them as part of their development iteration cycle works well.”

“I've found Playwright tests to be a decent way of getting Claude to do what you're talking about.”

“Ask it to install and use Playwright to confirm rendering and flow. ... it definitely helps cut down on bugs.”

“using Claude Code with Playwright tests as the feedback signal is a clever way to grind through the spec without losing your mind”

“exposing Playwright-level primitives to a foundation model is fundamentally the wrong interface”

“My main issue with Playwright (and chrome-devtools) is that they pollute the context with a massive amount of stuff.”

“Playwright's screenshot comparison (toHaveScreenshot) combined with proper wait strategies has gotten pretty solid.”

“Tools like Selenium and Playwright have introduced explicit waits, which observe the DOM. This helps, but doesn't solve everything.”

“Playwright has a driver for example and its far faster and less resource hungry than Chrome.”

“It comes with a nice overview page that shows all the failed tests including traces and screenshots.”

“Playwright really simplifies getting setup. It won't work for everyone, but within 30 seconds Playwright will download it's needed browsers along with a test runner.”

“playwright got a lot of things right. one of the big ones was a fast websockets+json way to drive the browser”

“it's fast, easy to use, has popular features like auto-waiting, integrated video recording”

“Playwright in vision mode (as opposed to using the default a11y tree) and Codex for understanding worked best”

“This, paired with chrome devtools and playwright, had been a real productivity booster for me, and is quite fun.”