Trip Builder V2

A travel companion to accompany your trip and help plan along the way.

Background

My role

Product designer, responsible for discovery, research, and redesign of the AI tool.

Timeline

5 Months (April 2025 -August 2025)

Tools

Figma, Illustrator, Photoshop, Userinterviews.com, unmoderated testing.

Trip planning can be one of the most exciting — and overwhelming — parts of travel. To make this process more intuitive and inspiring, Tripadvisor launched the GAI Trip Builder, an AI-powered planning tool designed to help travelers create personalized itineraries in minutes. The first version (V1) allowed users to input destinations and preferences, generating a complete, day-by-day trip itinerary using AI. While the feature saw strong initial engagement, continuous research revealed that travelers were using the tool in more exploratory, inspiration-driven ways rather than committing to fully structured plans.

Over the 6 months, our team conducted extensive user research and behavioral analysis to understand how travelers interacted with GAI Trip Builder. We observed that many users wanted to refine and customize their trips before saving them, and that the AI’s recommendations often felt too broad or “one-size-fits-all.” With these insights in hand, we set out to design and launch GAI Trip Builder V2 — a reimagined experience with a more flexible interface, a smarter recommendation engine powered by Tripadvisor’s semantic search model, and a greater sense of personalization and control for every type of traveler.

Problem

With the addition of AI increate a product that inspires users in their travel planning journey and helps them learn about

How might we allow users to refine and iterate their itineraries while inspiring them for their next travels?

Current landscape

With the introduction of Generative AI in early 2023, Tripadvisor took advantage of the new technology in order to

Key needs

  1. Access to personalized guidance from anywhere, especially while on the go. 

  2. Receive personalized recommendations for hotels, attractions & restaurants.

  3. Easily save & book recommendations & guidance. 

  4. Make confident, inclusive, community-backed travel decisions. 

  5. Maximize their time while in-destination (including transportation & logistics).

  6. Offer support for non-travel related questions.

By redesigning the user experience and introducing a new semantic search model that leverages Tripadvisor’s vast review data, V2 makes trip planning more dynamic, relevant, and user-driven — transforming the AI assistant from a static planner into a truly collaborative travel companion.

Final Designs

Final Designs

Entry points

A toggle approach on home gives AITA a consistent, easy-to-find location that encourages discovery without disrupting core flows. In-line entry points contextually allow the user to find relevant information and an opportunity for us to coach users on high value prompts.

Map view

Hierarchy is important within a small screen. By placing the map behind a secondary control, we help the AI summaries become the primary focus within the chat.

Sources

Each individual recommendation will display a community chip that shows the direct reviews and forum posts which helped inform the selection.

List and card view

Rather than creating a maze of text recommendations and coordinating cards at the end of the summary, we’re bringing the two together. Text recommendations sit within the same section as their cards giving users the context around the recommendation and enabling them to act on it

Prompting

Prompts will appear at the end of every AI chat response, helping the user understand the capabilities of the chat, as well as inspiring further conversation.