Back to Projects
active

GoTrip

An AI-powered travel planning platform that generates personalized itineraries using machine learning and real-time data from multiple travel APIs.

Tech Stack

Next.jsTypeScriptPythonFastAPIOpenAIPostgreSQLRedisTailwind CSS

Overview

GoTrip reimagines travel planning by combining AI-generated itineraries with real-time data from flights, hotels, and activities APIs. Users describe their ideal trip, and GoTrip creates a complete, day-by-day plan tailored to their preferences, budget, and travel style.

The Problem

Planning a trip typically requires hours of research across multiple platforms. GoTrip consolidates this into a single, intelligent experience.

Architecture

The platform uses a microservices architecture:

  • Frontend: Next.js with TypeScript for a responsive, fast UI
  • AI Engine: Python FastAPI service using OpenAI for itinerary generation
  • Data Layer: PostgreSQL for persistence, Redis for caching API responses
  • Integrations: Amadeus API (flights), Booking.com API (hotels), Google Places API (activities)

Key Features

  • Natural language trip description
  • AI-generated day-by-day itineraries
  • Real-time pricing from travel APIs
  • Collaborative trip planning
  • Export to calendar and PDF
  • Budget optimization suggestions

Challenges

The biggest challenge was balancing AI creativity with practical constraints. An AI might suggest visiting three cities in one day , we needed constraint systems to ensure itineraries were actually feasible.

Lessons Learned

Building GoTrip taught me that the best AI products don't just generate content , they understand context. Travel planning requires understanding geography, time zones, transit times, and personal preferences simultaneously.

Developer PortfolioView Portfolio