StickerGiant Brand Playbook

Turning brand guidance into usable data

StickerGiant already had brand guidance, but it lived in a PDF. A designer could look up a logo rule, but software could not query it, validate an asset against it, or use it in an automated workflow.

I rebuilt the guidance as structured data. The website, command-line tools, APIs, and automated reviews now use the same rules.

How people and software use it

The web interface lets people browse guidance, preview components, and edit rules through a CMS. A Python CLI lets AI tools fetch rules by category, check assets, and return structured responses. JSON manifests, API endpoints, an OpenAPI specification, and an MCP server make the same data available to automated workflows.

Every rule starts in JSON, so a new interface does not create another copy of the guidance.

What the playbook covers

The playbook includes color, type, logo usage, voice, accessibility requirements, and rules for when AI can act without review. Channel guides cover social, email, print, packaging, events, advertising, and web. It also links the data to Figma tokens, downloadable assets, and component documentation.

Setting limits for AI

The playbook assigns work to four levels:

• AI-final: Deterministic formatting, tags, and decorative images that require empty alt text.
• AI-assisted: An agent drafts, then a person reviews and approves. This includes alt text for meaningful images.
• Concept-only: An agent produces options, but a person chooses and rewrites the direction.
• Human-only: Crisis response, executive communication, and other brand-defining statements.

These levels are stored as data. An AI tool can check the rule before it starts a task.

Automated review

When content enters the review queue, the workflow identifies the channel and content type, fetches the relevant rules, checks the submission, and returns a decision with its reasons. Clear passes continue. Uncertain or sensitive work goes to a person.

This leaves people to review the work that actually needs judgment.

The stack

The public interface uses HTML, CSS, and JavaScript. Decap CMS handles editing. Netlify hosts the site and API functions. The Python CLI uses only the standard library. There is no build framework between the source data and the system requesting it.

My role

I designed the information model, wrote the brand and AI-governance rules, built the site and integrations, and connected the playbook to the workflows that use it.