Momentic Debuts Mo, AI Agent That Tests Apps Without Scripts

Momentic on Sept. 28 launched Mo, an AI agent that tests applications without a written test suite, SiliconAngle reports. Developers hand Mo an app URL and test credentials through a chat window or a command-line interface, and the system deploys a swarm of agents that click buttons, fill in fields and 'attempt thousands of permutations and edge cases.'

The pitch from co-founder and CEO Wei-Wei Wu is that scripted testing is on its way out. 'What is the next frontier of agentic quality? Our bet is that there's no tests in the future. It's just agents verifying it themselves, based off of your instructions,' Wu said. The maintenance tax is Wu's core complaint: 'As long as you have scripts somewhere in your codebase, someone has to maintain it.'

When Mo trips over something, 'it gives the developer a blow-by-blow of what was tested, what failed, how to reproduce the bugs and video evidence of each one.' Mo can also ingest product requirements documents, Jira issues, Linear tickets or Confluence pages for context, and convert its output back into a developer's chosen script format for teams that want to keep a suite around.

Momentic lists Notion, Superpower, Iris, Committee for Children and Boundless as customers. It lands in a coding-tools stretch dense with agent releases, including Anthropic's Claude Sonnet 5.5 earlier in the week.