36 / 168 · 01 Agent Skills for Browser Automation · Playwright Test Agents: Planner, Generator, Healer← prev⊞ allnext →☰ Read as one page
5.5Limits an Architect Should Name
- Non-determinism. Two planner runs produce different plans. Treat agent output like human output: reviewed, versioned, owned.
- Generated tests inherit generated blind spots. The planner tests what it can see. Business rules that live outside the UI (pricing math, permissions matrices) still need designed tests — see the AI-Augmented Test Design topic.
- Token cost lives somewhere. Agents explore the app through browser tooling; long exploration sessions are not free. The CLI's disk-first snapshots (previous chapter) are what make this affordable.
- Regenerate on upgrade. Agent definitions are Playwright-version-coupled; stale definitions are a real failure mode. Rerun
init-agentsas part of your Playwright upgrade checklist.