# I built an AI agent that runs manual test cases in a real browser

> Source: <https://dev.to/broxhq/i-built-an-ai-agent-that-runs-manual-test-cases-in-a-real-browser-4caj>
> Published: 2026-06-03 11:00:50+00:00

Every deploy — same manual test steps. Login, open the form,

fill the fields, check the result. Over and over.

I wanted to skip the Playwright/Selenium boilerplate and just

paste my existing test cases as plain text.

qpilot — an AI agent that reads your manual test case and

executes it in a real Chrome browser step by step.

You write this:

The agent opens Chrome, clicks, fills forms, and reports

pass/fail/warn per step with evidence from the page.

If it hits an OTP or captcha — it pauses and asks you directly.

npx qpilot

No code. No config. No Selenium.

TypeScript, Playwright, Claude Haiku via Anthropic API.

Open source: [qpilot](https://github.com/broxhq/qpilot)

Curious what you think — especially about edge cases

you'd want it to handle.