How I Started Using AI Agents for End-to-End Testing (Autonoma AI)

I’ve been thinking a lot about how broken testing workflows feel right now.

Most of the time, writing end-to-end tests is slow, brittle, and honestly kind of painful. You write selectors, they break when the UI changes, and suddenly half your tests are useless.

Recently, I came across Autonoma AI, and it feels like a completely different approach.

Instead of writing test scripts, you just describe what you want in plain English.

Something like: “Open the login page, enter credentials, and verify the dashboard loads.”

And that’s it.

Autonoma handles:

Running tests on real browsers and devices Detecting elements using AI instead of fragile selectors Automatically fixing tests when UI changes (self-healing)

That last part is huge. Anyone who’s worked with tools like Selenium or Cypress knows how annoying broken selectors can be.

What’s interesting is that this isn’t just a testing tool — it feels like part of a bigger shift toward LLM-native development.

Instead of writing code for everything, we’re starting to describe intent and let AI handle execution.

I can see this being useful for:

Startups that don’t want to maintain complex QA pipelines Teams shipping fast where UI changes constantly Solo devs who just want basic coverage without overhead

I haven’t fully integrated it into a production project yet, but even the idea of replacing brittle tests with something adaptive is pretty exciting.

Curious to see how this evolves.

Repo: https://github.com/autonoma-ai/autonoma