Hooray: A To-Do App That Judges You

Most to-do apps try to motivate you. They cheer you on, then go quiet the moment you skip half the list. For people raised on TikTok and instant rewards, that cheering wears off fast. Hooray does the opposite. It’s gloomy, and it makes fun of you, and building something mean on purpose was the most fun I had on a project. The attitude gets people in the door; the real goal underneath is helping them change a habit.

The mascot looks like it’s egging on your worst habits. It’s really pushing you off them. Nobody glued to their phone turns disciplined overnight. The app just has to be funnier than your excuses for not starting.

The mascot has eight faces. You don’t pick which one shows up. Your progress does. Each face was generated with ChatGPT Image 2: same character, different expression, tied to a completion range. The more you finish, the further it moves along: gloom → disdain → mock → stubborn → eyeroll → smirk → forced-smile → cracked. Do nothing and you get gloom. Finish everything and you don’t get a happy grin. You get a face that’s cracked from the effort. Most apps praise you for doing the bare minimum. This one makes you earn the reaction.

One rule kept it working: the mascot is a fixed image. It never gets recolored or restyled. Each screen swaps in a different face. Hand that job to an AI agent and it’ll repaint the character to match the color theme. Keep it as eight fixed images and it stays a character.

The jokes aren’t random. They’re sorted into groups by how much you’ve finished. Check off a task and the app pulls a fresh line from the group that matches your new progress. “Progress. Technically.” There’s no backend and no AI reading your mood. Just a percentage and a stack of pre-written lines. Cheerful apps say the same thing whether you did one task or ten, so people stop noticing. These jokes change with your progress, so people keep reading.

Hooray started with a complete app concept and a set of mascot faces from ChatGPT Image 2. From there, Claude wrote the design guideline: colors, typography, components, copy rules, and the mascot-to-progress mapping. That guideline directed Codex to build the full Figma file of 10 screens, components, and variants. Then Claude Code took those Figma frames and built the tap-through prototype, reading every value straight from the file instead of guessing. Four tools, four stages, about a week.

The AI agent kept fixing things that weren’t broken. It flagged the dark tab bar as a bug. It swapped the dark text on the yellow button to white. Both were deliberate design choices. Most of the work was QA: checking what the agent changed and pushing back.

The AI did the building. Deciding what to build was not its job. What lasted past the prototype was how I worked with the tools.

• Read values, don’t guess them. Give an AI one source of truth and a rule against guessing, and its front-end work goes from close-enough to matching the file.
• Once the mascot’s faces and jokes were written down as clear rules, even an AI tool could build the character without breaking it.
• The design work moved earlier. Less time drawing, more time deciding which of the AI’s “fixes” to reject.

Hooray is still a prototype. It’s not on the App Store yet, but it’s the one I’d most want to take further. The bet is simple. Maybe the same people who ignore motivational apps will actually use one that makes fun of them.