I built a product to test webapps like a user would

Show HN: UI testing using multimodal LLMs

Operating in show hn launch, I built a product to test webapps like a user would operates.

Profile

Hi HN,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 pr

Its activity falls under show hn launch; the profile below is assembled from public directory data.

Directory data places it at the Show HN launch stage.

Website: kodefreeze.com