Atlas › 01 Agent Skills for Browser Automation › Playwright Test Agents: Planner, Generator, Healer☰ Read as one page
Playwright Test Agents: Planner, Generator, Healer
5.1What ShippedWith v1.56 (and maturing through 1.61, current as of July 2026), Playwright gained three first-party test agents — not a bolted-on AI…5.2The Artifact LayoutThree conventions matter:5.3Why This Workflow Is the Right Division of LaborThe plan → generate → heal split mirrors how a senior QA engineer actually works, and it puts the human review where it's cheapest and…5.4The Healer Is Self-Healing Done HonestlyThe healer's loop: run the failing test → replay the failing step → inspect the live UI → propose a patch (new locator, adjusted wait…5.5Limits an Architect Should Name- Non-determinism. Two planner runs produce different plans. Treat agent output like human output: reviewed, versioned, owned. - Generated…5.6Interview Talking Point"We use Playwright's first-party test agents. The planner explores the app and writes Markdown plans into specs/; humans review the plans…