Helping people find a gym that fits.
An internal AI-assisted fitness-discovery prototype designed to use location and a short preference conversation to recommend three relevant gym options.
- Work
- AI product exploration and experience design
- Status
- Internal prototype, 2024 · Not launched as a consumer service
The product question
From a long list to a useful shortlist.
A list of nearby gyms does not necessarily help someone decide where to train. FitLocal explored how a short conversation about location and preferences could make that choice more manageable.
The 2024 prototype specification defined the conversation, gym matching and the information passed between them. Recommendations were constrained to the supplied catalog.
Inside the prototype
A guided way to find a fitness fit.
- 01
Locate
Start with a location and a supplied catalog of gyms.
- 02
Understand
Ask five to ten preference questions, one at a time.
- 03
Match
Select three gyms from the supplied catalog.
- 04
Return
Pass the selections and context to the application.
Prototype workflow overview.
What comes next
Test the quality of the choice.
A next evaluation would check whether each recommendation comes from the supplied catalog, fits the person’s stated preferences and has an explanation they understand.
What decision should your product make easier?
Bring the user need and the information people struggle to turn into a useful choice.