Mobile Design & DEVELOPMENT
The Best Move
Context aware food recommendation app
Tools
Figma · Claude Design· React
Scope of work
Developer · Designer
Duration
4 weeks
Challenge
What do I eat?
People who work out consistently face a recurring problem: knowing what to eat in real time, based on what they just did, what they're about to do, and what's actually in front of them. Existing apps require logging, tracking, or planning in advance, none of them meet the user at the moment of decision.
The Best Move operates at that exact moment. No tracking. No overthinking. The user opens the app, gives it three pieces of context, and gets a clear, contextual food recommendation in seconds.
SOLUTIOn
The Best Move is a real-time food decision support app for people who train. It is not a tracker, calorie counter, or meal planner. The entire product is built around one moment: the user is about to eat something and needs a clear, contextual recommendation immediately.
Location, Activity & Modifiers The Right Now flow starts with three quick context questions: where you are, how active you are, and whether anything else is affecting your day. Users pick from simple options, At Home or Out & About, their activity level, and lifestyle signals like alcohol or poor sleep. The whole thing takes under 30 seconds and sets the foundation for a recommendation that actually fits the moment.
Workout Type & Food Input: Once the context is set, users tell TBM about their workout the type and how soon it is then describe what's in front of them in plain language. No format required. Whether it's "grilled chicken, rice, broccoli" or "chips and pizza," the app interprets it and uses the workout timing to shape the recommendation around what the body actually needs right now.
The home screen tracks consistency over time with a Best Move Streak and weekly adherence rings, turning daily decisions into visible progress. After each food input, the app returns a clear next move direct, grounded in context, and followed by guidance on what to do after. No numbers, no tracking, just the clearest possible answer to "what should I eat right now?"
Key learnings
Designing for the moment
TBM had to work at the exact second a user is standing in front of food. That constraint shaped every design decision: fewer screens, faster inputs, no required formats. The value had to be immediate or it was nothing
Context is the product
The same Chipotle bowl means something completely different pre-workout versus post-workout. Building the contextual layer with modifiers, was not a feature, it was the core logic that made every recommendation worth it.
Prompt engineering is UX work
The AI output is what the user actually sees and acts on, which means the prompt is as much a design surface as the UI. Small changes to how context was structured and weighted produced dramatically different recommendation.
