AI-powered local discovery tool

An AI-powered travel and discovery platform that unifies eats, events, attractions, hotels, and experiences in one place.
Personalized
Interactive Map
Local Discovery
My Role:
Product Designer
Status:
Launched on web and iOS
Timeline:
March  - August 2025
Team:
1 Product designer, 1 Product manager, 2 AI Engineers, 5 Developers
Deliverables:
  • Revamped 80% of web and iOS interfaces, enhancing usability and consistency for 2M+ users.
  • Built a design system from scratch and established design guidelines to scale design quality.
  • Conducted user research to guide decisions.

Overview

About:
Wanderboat is an AI-powered local discovery platform that transforms how people find places to eat, explore, and stay. Unlike traditional search or generic AI summaries, it blends chat-based feeds with an immersive map, surfacing curated dining, events, attractions, hotels, and experiences — all grounded in real photos and videos from real people.

Impact

22%
in project-led user growth
27%
in user engagement with AI interactions and feature exploration.
15%
in average time spent on key pages

Problem

01: Despite the product’s potential, users struggled to understand what Wanderboat could do for them among so many AI tools.
02: Engagement was low, especially on the chat page — users didn’t spend much time exploring.
03: The homepage and chat experience both failed to guide users clearly or inspire interaction.
Old Design

How AI Works Here

Wanderboat’s AI analyzes millions of social posts and videos in real time, using a POI engine, Thinking Agent, and Vision Understanding to deliver personalized, trustworthy local recommendations.

User Study

Based on responses from 300 users, here are the main takeaways..
Overwhelming homepage layout
With chat input, event recommendations, and user posts all shown together, users felt uncertain about where to begin.
Users want timely, authentic, and personalized recommendations,
61.3% value fresh, updated suggestions, 52% want real photos and reviews, and 51% look for personalized suggestions based on their interests or mood.
Low engagement with features and AI
Users found AI results unclear and text-heavy, rarely engaging with recommendations, and wished for more map-based information on web and mobile.

Design Goals

01: Build trust through context-rich results
Replace information overload with curated, easy-to-scan feeds. Provide authentic visuals, key details, and map-based context so users feel confident clicking into AI recommendations.
02: Personalize results
Tailor recommendations to each user’s unique taste, adapting to their interests, moods, and preferences over time.
03: Establish a clear content hierarchy
Structure the chat page and homepage with a clear flow, guiding users on where to begin and reducing confusion, random clicks.

Ideas to action

Selected ideation drafts

I worked with engineers to validate feasibility and backend data support, and with AI experts to refine chat interactions, ensuring designs were both user-friendly and technically achievable.

Ideas to action

Personalized experience

Users want timely, authentic, and personalized recommendations

Solution:

1. Prioritized key features by placing planner, stays, and eats at the top of the homepage to increase visibility and improve navigation efficiency.

2. Enhanced engagement through visually rich suggested prompts that guided users toward exploration and deeper interaction with the AI chat.

3. Personalized recommendations by making prompts dynamic—tailored to user location, weather, and user interests selected during onboarding.

4. Introduced visual hierarchy by designing varying box sizes to add visual variety while scrolling, reserving larger boxes for more popular or important prompts.

Build trust through
context-rich results

Users found AI results unclear and text-heavy, rarely engaging with recommendations, and wished for more map-based information on web and mobile.

Solution:

1. Replace long text summaries with short, scannable descriptions paired with images or video snippets.

2. Rearrange map cards from the left to the bottom, giving more space to the map and encouraging users to interact with it as the primary discovery surface.

3. In addition to AI recommendations, both the map view and list view display suggested places, and users can quickly switch between them using the “Map & Moments” toggle.

3. User posts and short videos are displayed under the list view, offering authentic reviews that help users make more confident decisions, without needing to open multiple tabs or search across different platforms.

Establish a clear content hierarchy

With chat input, event recommendations, and user posts all shown together, users felt uncertain about where to begin.

Solution:

1. Onboarded first-time users with pre-set queries (e.g., “Find me a rooftop bar nearby,” “Show live music tonight”) to clearly communicate product value and reduce initial friction.

2. Established visual hierarchy by giving the right screen more space for exploration and discovery, dedicating room to rich visuals of events, restaurants, and activities to drive engagement, while keeping the left chat panel compact and accessible to support without competing for attention.

New Design
Old Design

user feedback