AI-powered QA automation portfolio

Agentic Testing Dashboard

A browser-driving AI testing agent that explores public demo applications, generates Playwright specs, runs them, repairs failures, and publishes test summaries.

3 Demo apps/flows
9 Committed tests passing
GPT-5 Generation model
2 days Target report retention

Current coverage

Public Demo Flows

Passed 3 tests

Sauce Demo Login

Validates login page controls, successful login, inventory visibility, and product detail navigation.

Target
saucedemo.com
Tools
Playwright, Chromium
Passed 3 tests

Sauce Demo Checkout

Covers login, add-to-cart, cart update, fake checkout, order completion, and return home.

Safety
Public demo checkout
Repair
Ready
Passed 3 tests

Shopify Demo Cart

Checks catalog content, product detail pages, safe add-to-cart behavior, and external link hrefs.

Target
sauce-demo.myshopify.com
Boundary
No real checkout

How it works

Agent Pipeline

  1. ExplorePlaywright opens the target page and the model chooses safe next actions.
  2. GenerateThe model turns the exploration trace into Playwright tests.
  3. ExecuteThe generated spec runs in Chromium with traces and screenshots on failure.
  4. RepairFailures are sent back to the model for selector and assertion repair.
  5. ReportRuns produce dashboard data and Playwright reports for review.

Next steps

Portfolio Roadmap

Live Report Publishing

Publish the latest dashboard and report artifacts to a stable URL.

Multi-Project Views

Group test suites by product, client demo, or application type.

Specialized Agents

Split exploration, repair, accessibility, and reporting into focused roles when complexity grows.