What was done in practice

Faced with a complete QA team turnover, a single test automation engineer planned and built a new QA architecture from scratch while simultaneously onboarding to an active codebase with no meaningful handover. The scope spans the full quality stack: E2E, unit, and component testing across frontend and backend, CI/CD pipeline configuration, and infrastructure management.

AI is integrated as a first-class tool via repository-level context files, dedicated test-writing guides, and custom AI skills. These encode project-specific patterns and conventions, enabling AI to transform product specifications into consistent, correct test code with minimal guidance. This accelerated framework development and test creation from months to weeks.

Beyond new development, AI facilitated a structural audit that identified critical issues like cascading failures and shared mutable state. The suite was redesigned into fully isolated, self-contained scenarios, improving coverage for complex billing logic and resolving long-standing flakiness in UI tests.

Results

The new TA Playwright framework, built from scratch in one month, executes API and UI tests across the live full stack in two environments, with tests redesigned as isolated, self-contained scenarios to resolve previous flakiness.

While formal metrics are pending, test coverage and delivery speed have improved together. AI accelerates every phase, from specs to code, providing a reliable 85–90% starting point that requires human refinement, hinging on high-quality documentation and project-specific conventions.

The work is still in progress, but the current state of the test suite across the project is as follows: