Momentic debuts Mo AI agent to automate software testing without scripts

Momentic has launched Mo, an AI agent built to test software without making developers maintain a pile of scripts. The pitch is simple enough: if code can now be written by humans or by AI agents, then testing should not have to be trapped in the old ritual of writing, fixing and rechecking brittle automation every time the app changes.

Co-founder and CEO Wei-Wei Wu is blunt about where he thinks this is heading. He told SiliconANGLE he believes the next step in agentic quality is a world with no tests at all, just agents verifying software directly from instructions. That is a pretty aggressive claim, but it fits the problem Momentic is trying to solve. In his view, once scripts exist anywhere in a codebase, somebody owns them. Somebody has to keep them alive.

Mo is meant to remove that middle layer. Instead of asking developers to create and maintain a second repository of browser tests, it lets them point the agent at an app and tell it what to do. The setup looks a lot like the AI coding tools developers already use: there is a web interface, a chat box, and a command-line interface for automation. Wu’s shorthand version of the workflow is basically: “Bug bash this app I just built. Here’s the URL. Here are some test credentials. Go ham.”

Once Mo gets going, it opens the app, spins up a swarm of agents and works through the interface. It can use a product requirements document, a Jira issue, a Linear ticket or a Confluence document when more context is needed. From there it tries thousands of permutations and edge cases, records every interaction, and then hands back a report showing what it tested, what broke, how to reproduce the bugs and video evidence of each failure.

Momentic says customers have been testing Mo over the past few weeks, including companies such as Notion, Superpower, Iris, Committee for Children and Boundless. The company’s core argument is that no one actually wants to write endless test scripts. They want software without bugs, and they want the testing burden to stop pretending it is the main event.