Product
MyTest
An AI QA platform where coding agents test your app and a second agent checks their work.
Visit the live siteMyTest is an AI QA platform. You describe your app and its key user journeys in plain English; MyTest creates testing agents, runs smoke tests against staging and saves the scenarios for future runs. A separate verifier agent re-runs each failure before it is reported as a bug.
Most AI testing demos stop at an agent clicking through an app. The harder problem is trust: a testing agent that reports a failure that is not real wastes the team's time. MyTest addresses this by separating the roles. One set of agents runs the scenarios; a second, independent verifier agent re-runs each failure and only confirms it as a bug if it reproduces. It works with Claude Code, Claude Desktop, Antigravity and PagePilot. MyTest is live and built with AI agents, Claude, MCP, Python and TypeScript, created by Sakthi Vignesh.
Why it matters
- Plain-English journeys become reusable agent test scenarios
- Every failure comes with evidence: screenshots, console logs and network traces
- A verifier agent reproduces failures before bug reports are filed, so flaky results do not clutter the bug board
Frequently Asked Questions
What does the verifier agent do?
It re-runs each failure the testing agents found and only reports it as a bug if it reproduces, which keeps flaky failures off the bug board.
How do I define what gets tested?
You describe the app and its key user journeys in plain English. MyTest turns them into scenarios that are saved and reused on future runs.
What evidence does a failure include?
Screenshots, console logs and network traces.
Let's talk
Ready to get started with MyTest?
Tell us about your project and we'll scope it out together — no commitment, no sales pitch.
- Personal reply — not an auto-responder
- Response within 24 hours
- No commitment, no sales pressure