24.Brand guide PDF vs. live site

Name: Dembrandt
Author: Dembrandt

DesignerQAAgency

Overview

Your brand guide says one thing. Your live site says another. Extract what actually shipped, compare it against the PDF, and get a concrete list of exactly where the brand broke down.

Brand guides and live products drift apart during sprints, handoffs, and quick fixes. The brand guide says the primary blue is #133174. Production says #1a3a8a. Nobody noticed. This workflow extracts the real token state from the live site and feeds both the extraction JSON and the original brand guide PDF into an AI agent. The agent compares them systematically, lists every divergence, and classifies each as intentional (a product-level decision) or drift (an unintended deviation). The output is a concrete remediation list, not a subjective visual review.

Extract live tokens

Terminal

dembrandt client.com --save-output

Claude Code prompt

# Drag extraction JSON and brand guide PDF into context, then:

"Compare this extraction against the brand guide PDF.

Output an ASCII table:

TOKEN | BRAND GUIDE | PRODUCTION | DELTA | CLASS

(class: intentional / drift / unknown)

Flag differences above 10% as ⚠️.

Intentional = documented exception or product-level decision.

Drift = production diverged without a clear reason.

End with a remediation list: drift items only, ordered by visual impact."

Output

Gap report: which production values diverge from the brand guide, by how much, and where.

More in AI Pipelines

21.Clone a brand's design language 22.Build a design system in Claude Code 23.Rebrand an existing application 25.Cross-app token comparison 26.Build a design system in Figma via MCP 27.Paste tokens to Figma Make 28.Improve a Google Stitch prompt with brand context 29.Generate a branded presentation 30.Find tokens that fit a page's purpose

Browse all

All recipes →

43 workflows