Skip to main content
Audit what’s actually on screen, not what a DESIGN.md says. The QA counterpart to the design pillar. It opens a rendered page in a real browser, reads its actual computed styles (the fonts, heading scale, and colors the browser resolved), and grades them deterministically — every finding is a pure function of the page, not an LLM opinion. With a report, it adds one more check: whether the rendered body font matches the brand’s typography choice from that report’s design system.

What it checks

Deterministic hard-rules over the rendered styles:
  • Fonts — more than three distinct families in use; a body face that’s one of the AI-default convergence-trap fonts (Inter / Roboto / system-ui / …).
  • Headings — a heading scale that isn’t monotonically decreasing (h1 ≥ h2 ≥ h3).
  • System match (when a report’s design system is supplied) — whether the rendered body font actually matches the brand’s typography choice.

What you get back

Needs the browser

Design review reads computed styles, which requires a script-capable renderer (Playwright):
A screenshot-only backend (Firecrawl) cannot read computed styles — design review raises a clear error pointing you to install the browser.