Synthesis
Design-intelligence report
Generate a unified design-intelligence report for any URL — score, drift, and AI readiness synthesized into one composite grade. One input, one output, one grade.
Fires /score (40-check audit), /drift (12-check drift radar), and /readiness (10-check AI readiness) in parallel, then computes a weighted composite: score × 0.5 + drift × 0.3 + readiness × 0.2.
What it does
The report engine fires three internal APIs in parallel against the target URL. Each engine independently fetches the page, extracts CSS and :root tokens, and runs its own checks. The results are then synthesized into a composite score using a weighted formula.
Weighting: score (50%) is the broadest quality measure — tokens, typography, motion, accessibility, anti-generic, runtime. Drift (30%) is the 2026 crisis — AI-generated UI drift, token fabrication, value variance. Readiness (20%) is the emergent axis — machine-readable tokens, llms.txt, agent.json, MCP, DESIGN.md.
Composite: round(score × 0.5 + drift × 0.3 + readiness × 0.2). Grade: A≥90, B≥80, C≥70, D≥60, F<60. 8 synthesis checks verify the report itself ran correctly.