Skip to main content
Home/Recipes/Cross-app token comparison
AI Pipelines

25.Cross-app token comparison

DesignerPMQAEnterprise

Overview

Large organizations often have a main site, a SaaS app, and a docs site, all drifting from each other without anyone noticing; extract all three and ask an AI to map what is shared versus what has diverged.

Large organizations run multiple digital products simultaneously: a marketing site, a SaaS application, a documentation portal, a mobile app, each maintained by different teams. Without a shared enforcement layer, the visual identity of each surface drifts independently. Extract tokens from all active surfaces, then ask an AI agent to compare them: which values are shared across all products (the true brand baseline), which differ by product (intentional product-level variation), and which differ inconsistently (unintentional drift that should be fixed).

Extract main site

Terminal
dembrandt company.com --save-output

Extract app

Terminal
dembrandt app.company.com --save-output

Extract docs

Terminal
dembrandt docs.company.com --save-output
Claude Code prompt
# If component-family-consistency skill is installed, activate it first.
# Load all three extractions, then:
"Compare these three token sets. Output two tables:
SHARED TOKENS (appear in all three with <10% variance):
TOKEN | VALUE | NOTES
DIVERGING TOKENS:
TOKEN | MAIN SITE | APP | DOCS | DELTA | VERDICT
(verdict: intentional variation / likely drift / confirm with team)
Flag any color that differs by more than 10% ΔE as ⚠️ drift.
Flag any spacing value that differs by more than 4px as ⚠️ drift.
Intentional variation = product-level UI convention (e.g. denser dashboard).
Drift = no plausible reason for the difference."
Output

Token overlap map: shared baseline vs. per-product overrides vs. unintentional drift.

Browse all

All recipes →

43 workflows