This blueprint evaluates a model's ability to generate simple, accessible, and semantically correct HTML for common web components. The prompts do not explicitly ask for accessibility features; the model is expected to produce high-quality, usable markup by default. Checks are based on fundamental principles of HTML semantics and WAI-ARIA practices.

This blueprint probes whether models default to a narrow, instantly-recognizable set of generative-UI conventions — cream/beige grounds with terracotta-orange accents, purple-to-blue gradient heros, a handful of "safe" sans-serif faces, the sparkle (✨) motif, centered-everything layouts, and interchangeable startup copy — or whether they can commit to a distinctive visual identity that actually fits the subject.

Every prompt asks for a single self-contained HTML document. Because judges read the raw HTML/CSS source, most tells are directly observable: font declarations, gradient definitions, the literal ✨ character, and boilerplate marketing phrasing. Deterministic checks form the backbone; LLM-judged points (phrased as positive, source-observable statements) cover palette and overall genericness.

Three prompt families:

• Strong-world subjects, given with NO style guidance — a generic SaaS treatment is self-evidently wrong for a doom-metal band or a Victorian funeral home.
• Explicit constraint-following — the prompt names conventions to avoid; does the model comply?
• Neutral SaaS bait — the exact context where the default aesthetic flourishes.

This blueprint evaluates a model's ability to generate simple, accessible, and semantically correct HTML for common web components. The prompts do not explicitly ask for accessibility features; the model is expected to produce high-quality, usable markup by default. Checks are based on fundamental principles of HTML semantics and WAI-ARIA practices.