In-depth project
breakdowns

A Playwright test framework with an autonomous AI agent built into the QA workflow. The agent maps existing coverage from spec files, browses the live app, and generates structured test cases for uncovered flows — then applies semantic deduplication before pushing to Qase TMS.

A Claude Code agent that automates used car research across Czech automotive portals — browsing listings, evaluating engine reliability, checking service history indicators, and generating structured buy / reconsider / avoid reports for every car it analyzes.