Launching a social travel app that tags every place with 98% AI accuracy
Industry
AI
Tools
Bubble
Services
Development
Design
Travel recommendations online come either from strangers or stripped of context, with maps showing pins and review sites showing ratings, and neither telling you whether a place actually fits the vibe you want. We built Vela, a social travel app where recommendations come from people you trust and AI tags every place at 98% accuracy. Now live across eight cities including Dubai, Paris, London and Bangkok.
- 2487
- 8
- 98%
Ramzi Nahawi had a clear frustration: travel recommendations online come either from strangers or stripped of context. Maps show pins, review sites show ratings, and neither tells you whether a place fits the vibe you are after or whether someone whose taste you trust has actually been there. Vela was built to fix that: a social travel app where recommendations come from people you follow, every place is intelligently tagged, and your Google Maps history carries over from day one.
This was always about weight. A recommendation had to carry real meaning, knowing the kind of experience a place delivers, a cocktail bar with a certain energy or a restaurant for Sunday lunch. The data came first, because a travel app lives on whether people can find the cities they want, so we rebuilt the underlying city data with the geographic context that makes each one unambiguous. Then we met people where their habits already were, with a two-way Google Maps integration that imports years of saved places on signup. The most careful work was making AI feel natural: when someone adds a place, Vela classifies the category and the feel automatically, and we tuned it until it reached 98% accuracy in beta, precise enough to run quietly in the background.
Vela launched as a web app and an iOS app, live across eight destination cities including Dubai, Paris, London and Bangkok, connecting travellers with expert local concierges and a community of curators sharing places they have actually been. The AI tags every place as it is added, at 98% accuracy, and a second phase, the full AI concierge, is already in development. The foundation is built to grow city by city.











