CmdRunner – Upload test cases and an AI agent runs them in a browser
Excel-to-test automation when Testim and Mabl already dominate this space.

Replaces manual Playwright scripting, but Claude-generated tests and GitHub Copilot already cover this.
QA engineers, test automation teams, startups without dedicated automation engineers
GitHub Copilot · Claude · Zapier's test generation
Excel-to-test automation when Testim and Mabl already dominate this space.
Generates edge cases from one recording, skipping the happy-path trap.
The write-up zeroes in on a concrete, painful failure mode: MCP setups streaming full DOMs and logs into models and burning token budgets. It shows how playwright-cli keeps browser state external and emits compact element references and YAML flows you can replay into npx playwright test — a realistic pattern for long agent sessions. Valuable practical guidance for teams already on Playwright, but it's an explainer, not a new system you can drop in without plumbing.
Session replay to test converter, but Replay.io and LogRocket already pivot toward this.
TDD-first auto-fix approach writes failing tests before generating patches, not just patching blindly.
Curated Playwright repo list, but remove.bg-level: a solved problem in a crowded space.