▸case-01 I'm starting a new SaaS analytics dashboard and need a full design system created. Please research similar market competitors online, evaluate design options with a safe versus risky trade-off breakdown, generate an HTML preview file demonstrating the system, and write the final design guidelines to a DESIGN.md file. | fail→fail | 28,292 | 6,353 | -78% | 1 | 1 | 0% | 6,200 | 612 | -90% | 0 | 0 | — |
▸case-02 We are building an e-commerce platform for artisanal coffee and need a comprehensive design system. Could you conduct market research on top retail brands, outline visual choices comparing conservative options against bolder ones, produce a standalone HTML page previewing the components, and document everything in DESIGN.md as our main reference? | fail→fail | 31,721 | 30,513 | -4% | 1 | 1 | 0% | 6,201 | 6,352 | +2% | 0 | 0 | — |
▸case-03 Our team is launching a developer tools web portal. Help us establish our brand identity and design rules from the ground up: search for competitive developer products for inspiration, provide a clear safe vs risk analysis of component decisions, generate a single-file HTML preview, and compile a DESIGN.md file. | fail→fail | 30,072 | 34,504 | +15% | 1 | 1 | 0% | 6,200 | 6,351 | +2% | 0 | 0 | — |
▸case-04 We are developing a mobile banking web client for managing personal finances. Create our core design system from scratch. Look up rival consumer finance apps for market standards, evaluate styling trade-offs using a safe and risky framework, provide an HTML preview document showing interactive elements, and write our design standards into DESIGN.md. | fail→fail | 31,898 | 35,135 | +10% | 1 | 1 | 0% | 6,203 | 6,354 | +2% | 0 | 0 | — |
▸case-05 Our digital health team is launching a patient tele-health portal. We need an end-to-end design system created from the ground up. Perform market research on leading telehealth services, assess design options using a explicit safe versus risk trade-off model, output a single-page HTML file previewing components, and generate DESIGN.md. | fail→fail | 33,652 | 34,383 | +2% | 1 | 1 | 0% | 6,209 | 6,360 | +2% | 0 | 0 | — |
▸case-06 We are building an online learning platform for interactive coding tutorials. Establish our visual guidelines and design system from scratch. Conduct web research on existing e-learning platforms, evaluate component decisions through a safe vs risk trade-off analysis, generate an HTML component preview page, and publish the design rules in DESIGN.md. | fail→fail | 40,626 | 32,070 | -21% | 1 | 1 | 0% | 6,203 | 6,354 | +2% | 0 | 0 | — |
▸case-12 We are developing a fleet tracking UI for cargo shipments. Create a complete design system from scratch. Examine current enterprise logistics software for visual standards, structure design choices into safe versus risk trade-offs, deliver a functional HTML preview, and document the system in DESIGN.md. | fail→fail | 33,172 | 30,980 | -7% | 1 | 1 | 0% | 6,195 | 6,346 | +2% | 0 | 0 | — |
▸case-07 Our property search startup needs a comprehensive design system for listing homes. Search contemporary real estate platforms for design inspiration, present a clear safe versus risky trade-off breakdown of styling choices, render a single-file HTML preview, and save the design specification to DESIGN.md. | fail→fail | 34,305 | 9,851 | -71% | 1 | 1 | 0% | 6,195 | 545 | -91% | 0 | 0 | — |
▸case-08 We are building a workout and nutrition tracking web app. Help us build a design system from scratch: perform competitive research on popular health apps, analyze design directions with a safe vs risk breakdown, build a self-contained HTML page previewing card and input components, and write DESIGN.md. | fail→fail | 29,752 | 29,281 | -2% | 1 | 1 | 0% | 6,199 | 6,350 | +2% | 0 | 0 | — |
▸case-09 Our team is launching a flight and hotel search booking engine. Construct a complete design system for us. Inspect leading travel portals to benchmark industry conventions, present safe and risk trade-off options for typography and UI elements, produce a standalone HTML preview file, and save everything in DESIGN.md. | fail→fail | 33,786 | 30,706 | -9% | 1 | 1 | 0% | 6,199 | 6,350 | +2% | 0 | 0 | — |
▸case-10 We are creating a streaming community discussion board. Construct a design system from scratch. Benchmark current gaming forums via web search, provide a safe versus risk analysis of color palettes and components, deliver an HTML page displaying component samples, and record the results in DESIGN.md. | fail→fail | 34,362 | 7,863 | -77% | 1 | 1 | 0% | 6,194 | 484 | -92% | 0 | 0 | — |
▸case-11 Our security operations center needs a unified visual style for threat monitoring views. Build a design system from scratch by researching existing SOC dashboards, analyzing visual choices with a safe versus risk breakdown, providing an HTML preview page, and writing DESIGN.md. | fail→fail | 26,096 | 32,289 | +24% | 1 | 1 | 0% | 6,189 | 6,340 | +2% | 0 | 0 | — |
▸case-13 Our startup is building a multi-chain wallet web interface. Establish our visual language and design system from scratch: research top decentralized wallet designs, evaluate component decisions using a safe versus risk matrix, provide a single-file HTML preview, and save the resulting specification in DESIGN.md. | fail→fail | 34,152 | 30,378 | -11% | 1 | 1 | 0% | 6,197 | 6,348 | +2% | 0 | 0 | — |
▸case-14 We are launching an independent news media outlet. Design our visual language and design system from scratch. Benchmark top digital news publications online, analyze layout choices with a safe vs risk trade-off breakdown, generate a standalone HTML preview document, and create DESIGN.md. | fail→fail | 35,008 | 39,627 | +13% | 1 | 1 | 0% | 6,193 | 6,344 | +2% | 0 | 0 | — |
▸case-15 We need a visual identity and component design system for an employee onboarding web platform. Conduct research on current HR enterprise platforms, present design choices with explicit safe and risk trade-offs, construct an HTML preview page, and output DESIGN.md. | fail→fail | 28,834 | 33,685 | +17% | 1 | 1 | 0% | 6,188 | 6,340 | +2% | 0 | 0 | — |
▸case-16 We are building a dining table reservation system for hospitality clients. Create a complete design system from scratch: examine contemporary restaurant booking platforms online, compare choices using a safe versus risk breakdown, deliver a single-file HTML preview of components, and output DESIGN.md. | fail→fail | 28,853 | 31,324 | +9% | 1 | 1 | 0% | 6,193 | 6,344 | +2% | 0 | 0 | — |
▸case-17 Our concert ticketing service needs a unified design system created from the ground up. Research live event platforms online, organize component options into safe and risk visual directions, produce a self-contained HTML preview, and write DESIGN.md as our main reference. | fail→fail | 30,151 | 35,196 | +17% | 1 | 1 | 0% | 6,190 | 6,341 | +2% | 0 | 0 | — |
▸case-18 We are developing a podcast streaming web client. Create our design system from scratch. Inspect current podcast streaming portals for standard practices, evaluate visual choices with a safe vs risk trade-off structure, output an HTML preview page, and store the system rules in DESIGN.md. | fail→fail | 33,358 | 32,405 | -3% | 1 | 1 | 0% | 6,195 | 6,346 | +2% | 0 | 0 | — |
▸case-19 Our IoT company is building a web controller for smart home devices. Establish a comprehensive design system from scratch: research modern smart home web interfaces online, outline safe versus risk design alternatives, provide an HTML component preview page, and write DESIGN.md. | fail→fail | 31,114 | 34,671 | +11% | 1 | 1 | 0% | 6,190 | 6,341 | +2% | 0 | 0 | — |
▸case-20 Our existing landing page header has an alignment bug where logo text overlaps the navigation menu on screen widths below 768px in flexbox layout. Can you review this snippet and suggest the specific CSS rule fix for display flex? | pass→pass | 5,921 | 8,474 | +43% | 1 | 1 | 0% | 1,038 | 1,696 | +63% | 0 | 0 | — |
▸case-21 We have an existing form modal on our live site. Could you evaluate the contrast ratio of `#888888` text on `#FFFFFF` background against WCAG 2.1 AA requirements and provide a pass or fail judgment? | pass→pass | 10,361 | 8,317 | -20% | 1 | 1 | 0% | 1,610 | 1,821 | +13% | 0 | 0 | — |
▸case-22 Here is our existing React Button component implementation. Write a Jest and React Testing Library test script to verify that the `onClick` handler fires when clicked. | pass→pass | 5,793 | 6,484 | +12% | 1 | 1 | 0% | 1,144 | 1,313 | +15% | 0 | 0 | — |