Vision-based Agentic testing automation with device CLI for mobile apps and games - real devices iOS & Android. Supports native (swift, kotlin), react native, flutter, KMP, unity and any mobile apps and games.

Framework-agnostic E2E testing principles and AI-assisted workflows for coding agents

Agentic cost & efficiency regression gate for AI agents — UiPath AgentHack 2026 (Test Cloud). Catches when an agent change makes it more expensive per successful outcome and blocks promotion before it ships.

Open-source automated voice testing for contact centers — real calls, real CRM verification. Salesforce Service Cloud Voice + Amazon Connect + Twilio.

A declarative API testing framework built on Playwright

Play the game from the popular YouTube series Story Warz by passing a device around with friends. A react website, protected with Agentic QA.

Human-style deterministic TypeScript + Playwright QA agent for CRM testing with Excel evidence reports

A production-grade Ruby Order Management API secured with Keycloak/JWT, featuring an 'Agentic' BDD automation framework that auto-extracts database error logs upon test failure.

Manual QA testing practice project using a real e-commerce website. Includes test plan, test scenarios, test cases, RTM, bug report templates, and reusable QA skills designed with Copilot-assisted workflow.

Full-stack Airbnb-clone demo app for the TestMu AI Cloud GitHub App (KaneAI), showcasing AI-native PR quality validation with preview deployments.

Beyond Vibe Coding - From Coder to AI-Era Developer - Talking About Testing Book Club

Autonomous black-box web app testing. Point it at any URL — it discovers and executes core user flows, generates a full HTML report with screenshots, traces, and AI-written failure analysis. Built as a Claude Code skill.

A hybrid testing runner for AI agents: write high-level plans for fresh code, execute deterministic steps directly, and use LLMs only where runtime interpretation is needed.

A browser agent explores Amazon checkout, a Neo4j graph ingests what it sees, and the graph reasons about the scenarios the agent missed — then feeds them back so the crawler tests them. Includes a production-architecture write-up.

📷🎨 If you could playwright, then you can screenshot. Vitest + screenshot automation, for product mockup, docs automation, agent verify, and many more.

A progressive QA curriculum — 23 tutorials from Playwright basics to AI agent testing, prompt injection, RAG evaluation, and production monitoring