Catch bugs by exploring web and mobile apps with QA agents
Momentic's agents autonomously plan, explore and bug-bash user flows in web, iOS and Android apps for engineering teams. ·
Done with a custom-built or unnamed agent
- What they did
- Mo is Momentic's AI QA agent. It runs autonomous sessions in the cloud, on web or hosted Android and iOS devices, with your org's MCP servers and secrets attached. Teams write flows in plain-English YAML and add product rules to a Knowledge base. The explore agent, run through the CLI, can produce bug reports with repro steps. Triage agents classify failures and propose repairs for a person to review. Tests can also gate CI.
- How it went
- Momentic reports 117,010 bugs caught. Its examples include a skipped 2FA step and saved cards dropped at checkout. Customer figures include Quora's daily test run falling from 7 hours to 30 minutes. These are the vendor's own claims.
- Worth knowing
- Auto-heal repairs and triage fixes arrive as proposed diffs that a person must review. Mo itself is in private beta, according to the changelog.
Try it yourself with Claude in Chrome
Open my web app at [URL] and log in with the test account [test account details]. Explore the [user flow, e.g. signup and checkout] like a QA tester: try normal paths, then edge cases like empty fields, wrong input, and back-button use. Finish with a list of bugs, each with steps to reproduce, expected versus actual behavior, and a severity. Do not submit real payments or delete any data; pause and ask me first if a step would do that.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Discussion on HN · Nov 2, 2026
Related use cases
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Add a third-party API integration via Devin PR
Devin opened a PR with the endpoint and backend wiring that was merged, but missed API key logic, code style and abstraction, needing review fixes.
Build a clinic app with booking and trackers
A doctor with no coding experience used Replit to build a clinic app in 5 days with booking integration, prescription requests, health trackers and an AI symptom checker.
Auto-open fix PRs from Sentry and log alerts
A Grok Bot called Sentinel monitors Sentry and logs and opens PRs on several repositories when triggers fire; still very early.
Run Codex with low-touch planning and port reservation
A commenter has Codex execute mostly on its own with human planning and review, including a portbroker that reserves and injects a port.
Fix bugs and release an app remotely via Telegram command
A commenter tells Gemini over Telegram to fix bugs, test, and release their app while they are away from their laptop.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.