Momentic, a Y Combinator startup, built AI agents that click through web and mobile apps to find bugs, which could save small teams hours of manual checking.
A startup called Momentic has launched software that tests apps the way a person would. Its AI agents plan a route through an app, click the buttons, and report what breaks. The founders, Wei-Wei and Jeff, announced it on Hacker News, where the post passed 100 points. Momentic is part of Y Combinator's W24 batch.
Momentic calls its agent an AI QA engineer. QA means quality assurance, the job of checking that software works before customers see it. The agents explore controls and user flows in web, iPhone and Android apps. Desktop apps are listed as coming soon.
Tests are written in plain English and saved as files in a team's code, so people can review them. One example on the company's page checks a store checkout. It logs in, adds a backpack to the cart, confirms the item total matches, and clicks the final button.
Teams can also run the tests from the command line as part of their release process. A failed test can then block a change from going live. Developers who use AI coding tools can have those tools write tests too.
Apps change often, and old tests tend to break when a button moves or gets renamed. Momentic says it finds controls again when the screen changes during a test run. It can also propose a permanent fix to the test file for a person to approve. One example shows a button label changing from Finish to Place Order.
When a test fails, the tool shows the failing step, screenshots and traces. It then sorts the problem into one of three types:
The material does not give pricing or say how the tool performs in independent tests. The praise on the company's site comes from its own customers. One says tests run 3x faster to write and maintain. Another says a 110-prompt check took 14 minutes instead of well over an hour.
The tool is aimed at teams that ship apps often and spend hours checking them by hand. A business that pays for an app may want to ask its developers whether automated testing like this could catch problems before customers do.
Momentic offers AI testing for web and mobile apps, but pricing and independent results are not yet public, so treat its claims as early.
EA has re-released 25 classic PC games at a discount until November 19, and Bethesda has finally given The Elder Scrolls VI a subtitle: Sentinel.
Read more: EA brings 25 classic PC games back, and Elder Scrolls VI gets a nameOpenAI released a ChatGPT for analysts and bankers that shows where each number came from, a feature that could matter well beyond finance.
Read more: OpenAI launches a ChatGPT built for Wall Street analystsA Kuala Lumpur firm now sells a SGD 1,500 check of what ChatGPT, Gemini, Perplexity and Google say about a named executive, after its founder's own test found mix-ups.
Read more: New Audit Checks What AI Chatbots Say About Business Leaders
