And join our discord to follow along!

I built this tool to solve the "flakiness" problem in UI testing. Existing AI agents often struggle with precise interactions, while traditional frameworks (Selenium/Playwright) break whenever the DOM changes.

The Approach: Instead of relying on hard-coded selectors or pure computer vision, I’m using a multi-agent system powered by multimodal LLMs. We pass both the screenshot (pixels) and the browser context (network requests, console logs, etc) to the model. This allows the agent to:

"See" the UI like a user and accurately map semantic intent ("Click the Signup button") to precise coordinates even if the layout shifts.

The goal is to mimic natural user behavior rather than following a predefined script. It handles exploratory testing and finds visual bugs that code-based assertions miss.

I’d love feedback on the implementation or to discuss the challenges of using LLMs for deterministic testing.

Comments URL: https://news.ycombinator.com/item?id=46572553

Points: 1

# Comments: 0

The approach used is a multi-agent system that uses an augmented vision based approach for interacting with the UI, rather than relying on the DOM. The goal is to mimic how your users would naturally use the UI, rather than following a predefined path.

I built this because I got tired of doing manual QA for my last SaaS product. I couldn't trust automated UI tests (Selenium/Playwright) because they were flaky, broke whenever the DOM changed, and missed obvious usability bugs.

Happy to answer any questions about it here, and would love your feedback.

Thanks!

Comments URL: https://news.ycombinator.com/item?id=46510066

Points: 2

# Comments: 2

I was a fan of their initial product but I find it slower than chatpgpt agent mode. And the pricing is not great for individual users.

I built this because I got tired of doing manual QA for my last SaaS product. I couldn't trust automated UI tests (Selenium/Playwright) because they were flaky, broke whenever the DOM changed, and missed obvious usability bugs.

We are completely bootstrapped, but we want to gather as much feedback as possible in these early days, so we have made the product available for free (for now).

Happy to answer any questions about it here, and would love your feedback.

Thanks!

Comments URL: https://news.ycombinator.com/item?id=46316095

Points: 3

# Comments: 0

Support for being able to receive email/custom actions is on our roadmap, but would love to see if getting this far would be valuable to you. The test was with the email=test@kodefreeze.com.

Please let us know if you have any feedback!

For instance, we were running a test case on a e commerce website and they have a random popup that used to come up after initial Dom was rendered but before action could be taken. This would confuse the LLM for the next action it needed to take because it didn't know the pop-up came up.