AI/MLexperimental

AI Testing Agent

An AI agent that automatically generates and runs end-to-end tests by understanding your application - Playwright under the hood.

View Source

Technology Stack

OpenAIPlaywrightTypeScriptComputer Vision

Capabilities

Features Explored

Key capabilities implemented in this experiment

feature_01.ts

Automatic test generation

feature_02.ts

Visual regression detection

feature_03.ts

Self-healing selectors

feature_04.ts

Natural language test descriptions

feature_05.ts

CI/CD integration via the CI/CD playbook

Insights

Key Learnings

What I discovered while building this

Vision models help understand page structure for test generation

Self-healing selectors reduce test maintenance significantly

Generated tests work best for happy paths, edge cases need human input

See the AI agent orchestration blueprint.

Note: This is an experimental project in the experimental stage. It represents a learning exercise and technical exploration rather than a production-ready solution. Code and patterns may change significantly.

AI/ML

Related Experiments

Other explorations in this area

beta

AI Code Review Assistant

An experimental AI-powered code review tool that provides contextual feedback, suggests improvements, and identifies potential bugs before they ship.

alpha

AI Form Generator

Describe a form in natural language and generate a fully functional, validated form with proper field types and accessibility.

experimental

Voice-First Interface

Exploring voice interactions for web applications with real-time transcription and natural language commands.

Interested in this technology?

I'm always happy to discuss experiments and share learnings. Let's connect if you're exploring similar ideas.

Get in Touch

Local-First Sync Engine

Edge Rate Limiter