Launching a social travel app that tags every place with 98% AI accuracy

  • Industry

    AI

  • Tools

    • Bubble

  • Services

    • Development

    • Design

  • 2487

    Users at Launch

    Users at Launch

  • 8

    Destinations

    Destinations

  • 98%

    AI Tagging Accuracy

    AI Tagging Accuracy

  • 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.

  • Vela case study screenshot
    Vela case study screenshot
    Vela case study screenshot
    Vela case study screenshot
    Vela case study screenshot
    Vela case study screenshot
  • Vela case study screenshot
    Vela case study screenshot
    Vela case study screenshot
    Vela case study screenshot
    Vela case study screenshot

Next Case Study

Moving a Finance SaaS Off Wix and Onto Framer in 6 Weeks

Highpath is a funding workspace for founders, CFOs and financing partners. We migrated their site off Wix Studio, rebuilt it as a 20-page site in Framer, and turned one flat website into three role-based buyer journeys, with tracking carried across and no downtime.

  • Framer

Finance

Highpath on a laptop

Moving a Finance SaaS Off Wix and Onto Framer in 6 Weeks

Highpath is a funding workspace for founders, CFOs and financing partners. We migrated their site off Wix Studio, rebuilt it as a 20-page site in Framer, and turned one flat website into three role-based buyer journeys, with tracking carried across and no downtime.

  • Framer

Finance

Highpath on a laptop

Moving a Finance SaaS Off Wix and Onto Framer in 6 Weeks

Highpath is a funding workspace for founders, CFOs and financing partners. We migrated their site off Wix Studio, rebuilt it as a 20-page site in Framer, and turned one flat website into three role-based buyer journeys, with tracking carried across and no downtime.

  • Framer

Finance

Highpath on a laptop

A 6B-view creator network, off Webflow and onto a site its team runs

Bent Pixels runs a YouTube creator network with more than 6 billion monthly views. Its Webflow site had stopped keeping up, and the plan to fix it was a day of AI prompts.

Instead, we moved it from Webflow to Framer in six weeks, gave the team a site they run themselves, and then extended into decks, call backgrounds and social assets.

  • Framer

Media

Bent Pixels on a studio display

A 6B-view creator network, off Webflow and onto a site its team runs

Bent Pixels runs a YouTube creator network with more than 6 billion monthly views. Its Webflow site had stopped keeping up, and the plan to fix it was a day of AI prompts.

Instead, we moved it from Webflow to Framer in six weeks, gave the team a site they run themselves, and then extended into decks, call backgrounds and social assets.

  • Framer

Media

Bent Pixels on a studio display

A 6B-view creator network, off Webflow and onto a site its team runs

Bent Pixels runs a YouTube creator network with more than 6 billion monthly views. Its Webflow site had stopped keeping up, and the plan to fix it was a day of AI prompts.

Instead, we moved it from Webflow to Framer in six weeks, gave the team a site they run themselves, and then extended into decks, call backgrounds and social assets.

  • Framer

Media

Bent Pixels on a studio display

Training a $1bn HR company to become AI builders and save $105k a year

Oyster is a $1.2bn global employment platform, an Employer of Record that helps companies hire, pay and support teams across 180+ countries, and they wanted that capability to live inside their own people. So we ran the AI Accelerator, a six-week n8n programme that took ~20 people from Legal, HR, Payroll, Product and Revenue Operations, most starting from zero, and turned them into builders who now ship and maintain their own workflows. Oyster's own measurement: $105k a year and 3,658 hours given back to teams with all their live automations.

This is for operations, HR or finance leaders who want their own people to build and own automations, not a build they cannot change themselves. If that is you, book a call.

  • n8n

HR

Oyster on a laptop

Training a $1bn HR company to become AI builders and save $105k a year

Oyster is a $1.2bn global employment platform, an Employer of Record that helps companies hire, pay and support teams across 180+ countries, and they wanted that capability to live inside their own people. So we ran the AI Accelerator, a six-week n8n programme that took ~20 people from Legal, HR, Payroll, Product and Revenue Operations, most starting from zero, and turned them into builders who now ship and maintain their own workflows. Oyster's own measurement: $105k a year and 3,658 hours given back to teams with all their live automations.

This is for operations, HR or finance leaders who want their own people to build and own automations, not a build they cannot change themselves. If that is you, book a call.

  • n8n

HR

Oyster on a laptop

Training a $1bn HR company to become AI builders and save $105k a year

Oyster is a $1.2bn global employment platform, an Employer of Record that helps companies hire, pay and support teams across 180+ countries, and they wanted that capability to live inside their own people. So we ran the AI Accelerator, a six-week n8n programme that took ~20 people from Legal, HR, Payroll, Product and Revenue Operations, most starting from zero, and turned them into builders who now ship and maintain their own workflows. Oyster's own measurement: $105k a year and 3,658 hours given back to teams with all their live automations.

This is for operations, HR or finance leaders who want their own people to build and own automations, not a build they cannot change themselves. If that is you, book a call.

  • n8n

HR

Oyster on a laptop

Frequently Asked Questions

    • Can Bubble handle an app with serious AI in it?

      Vela runs AI tagging on every place a user adds, hitting 98% accuracy in beta. The AI is invisible to the user and runs at scale on Bubble. The constraint isn't the AI itself, it's the prompt design and data structure around it.

    • We need a Google Maps integration that actually works. Can you do that?

      Vela's Google Maps integration runs both ways. Users import their saved places on signup and export trips back before they travel. The hard part is the trust signals around the integration, not the connection itself.

    • Our beta is getting feedback that the data isn't rich enough. Can you fix things like that without rebuilding?

      Vela hit the same wall. The city database wasn't distinguishing places with the same name. We rebuilt the underlying data layer without disrupting users. Most data problems are fixable inside the existing architecture if it was designed properly the first time.

    • How do you decide what's in the MVP and what waits?

      For Vela, the full AI concierge is in phase two. Phase one shipped the AI tagging, social discovery, and Google Maps sync because those were the moves that mattered for launch. Discovery is where we decide what version one needs to do.

    • Do you also build the iOS app, or just the web platform?

      Vela launched as a web app and an iOS app from the same Bubble build. We use BDK to deploy native to the stores without writing custom code. One product, multiple surfaces, no parallel teams.

Frequently Asked Questions

    • Can Bubble handle an app with serious AI in it?

      Vela runs AI tagging on every place a user adds, hitting 98% accuracy in beta. The AI is invisible to the user and runs at scale on Bubble. The constraint isn't the AI itself, it's the prompt design and data structure around it.

    • We need a Google Maps integration that actually works. Can you do that?

      Vela's Google Maps integration runs both ways. Users import their saved places on signup and export trips back before they travel. The hard part is the trust signals around the integration, not the connection itself.

    • Our beta is getting feedback that the data isn't rich enough. Can you fix things like that without rebuilding?

      Vela hit the same wall. The city database wasn't distinguishing places with the same name. We rebuilt the underlying data layer without disrupting users. Most data problems are fixable inside the existing architecture if it was designed properly the first time.

    • How do you decide what's in the MVP and what waits?

      For Vela, the full AI concierge is in phase two. Phase one shipped the AI tagging, social discovery, and Google Maps sync because those were the moves that mattered for launch. Discovery is where we decide what version one needs to do.

    • Do you also build the iOS app, or just the web platform?

      Vela launched as a web app and an iOS app from the same Bubble build. We use BDK to deploy native to the stores without writing custom code. One product, multiple surfaces, no parallel teams.

Frequently Asked Questions

    • Can Bubble handle an app with serious AI in it?

      Vela runs AI tagging on every place a user adds, hitting 98% accuracy in beta. The AI is invisible to the user and runs at scale on Bubble. The constraint isn't the AI itself, it's the prompt design and data structure around it.

    • We need a Google Maps integration that actually works. Can you do that?

      Vela's Google Maps integration runs both ways. Users import their saved places on signup and export trips back before they travel. The hard part is the trust signals around the integration, not the connection itself.

    • Our beta is getting feedback that the data isn't rich enough. Can you fix things like that without rebuilding?

      Vela hit the same wall. The city database wasn't distinguishing places with the same name. We rebuilt the underlying data layer without disrupting users. Most data problems are fixable inside the existing architecture if it was designed properly the first time.

    • How do you decide what's in the MVP and what waits?

      For Vela, the full AI concierge is in phase two. Phase one shipped the AI tagging, social discovery, and Google Maps sync because those were the moves that mattered for launch. Discovery is where we decide what version one needs to do.

    • Do you also build the iOS app, or just the web platform?

      Vela launched as a web app and an iOS app from the same Bubble build. We use BDK to deploy native to the stores without writing custom code. One product, multiple surfaces, no parallel teams.

Goodspeed logo icon

Join our newsletter

© 2026 Copyright. All Rights Reserved.