DirectBooker x ChatGPT — Xuewei Jiang

DirectBooker × ChatGPT

Designing a conversational hotel booking experience inside ChatGPT — surfacing direct prices, loyalty benefits, and exclusive perks at the exact moment of intent.

A new surface for an old problem

When OpenAI launched its Apps SDK and Model Context Protocol in early 2025, it opened a new distribution channel — one where users arrive with active, open-ended intent. Travel planning is a natural fit: most people begin with vague questions ("Where should I stay in Kyoto in May?") rather than rigid filter inputs.

DirectBooker, as a platform that focused on restoring power to direct hotel bookings, saw an opportunity. OTAs dominate hotel discovery online — they obscure direct prices, hide loyalty tiers, and capture margin that could go back to travelers. The ChatGPT canvas offered a way to intercept users before they defaulted to Booking.com or Expedia.

How do you design a product that lives entirely within conversation — no persistent UI, no page navigation, just text and intent?

Problem & Goals

OTA algorithms are designed to maximize their own revenue, not the traveler's value. Direct booking benefits — better cancellation terms, loyalty points, room upgrades, breakfast perks — are invisible on aggregator pages. Most users don't know what they're missing.

Goals

Drive efficient hotel discovery through conversational AI
Surface direct prices, loyalty benefits, and exclusive perks at high-intent moments
Increase trust and conversion for direct bookings

Research - Understanding how travelers actually think

Before designing any flows, I ran a discovery sprint — competitive analysis, user interviews, and behavioral walkthroughs — to understand where OTA discovery breaks down and what conversational AI could uniquely address.

Analyzing product references from ChatGPT OTAs and Perplexity to inspire location-based features and search capabilities.

Key Findings

Search is too rigid.
Users want to start with intent ("somewhere warm, boutique, good for remote work") not pre-defined filters. Existing tools force structure before trust is established.
Price comparison is opaque.
6 out of 8 users tested didn't know that direct prices are often equal or lower — they assumed OTAs had the best deals by default.
Loyalty benefits are invisible.
Users who belonged to hotel loyalty programs frequently didn't know how to apply or compare benefits — especially across an unfamiliar property.
Conversation reduces friction.
Prototype testing showed that users spent 40% less time finding a shortlist when they could describe their needs in plain language vs. using form filters.

From vague intent to confident booking

The core design challenge was mapping the messy, nonlinear reality of travel planning onto a reliable, sequential conversational flow — without making it feel like a form disguised as a chat.

In a chat-native product, the words are the interface. I spent as much time on response structure, tone, and information hierarchy as I would on visual components in a traditional product.

What we tried, what we cut

Not every approach made it to the final product. Here are three directions we explored and the rationale behind the decisions.

The product we shipped

The final DirectBooker app in ChatGPT is an opinionated conversational assistant — it asks fewer questions, surfaces more relevant context, and makes direct booking feel like the obviously smarter choice.

ROLE

Lead Product Designer

TIMELINE

2025 – Present

PLATFORM

ChatGPT Apps (MCP)

TEAM

Design · Eng · Product

A new surface for an old problem

Problem & Goals

OTA algorithms are designed to maximize their own revenue, not the traveler's value. Direct booking benefits — better cancellation terms, loyalty points, room upgrades, breakfast perks — are invisible on aggregator pages. Most users don't know what they're missing.

Goals

Drive efficient hotel discovery through conversational AI

Surface direct prices, loyalty benefits, and exclusive perks at high-intent moments

Increase trust and conversion for direct bookings

Research - Understanding how travelers actually think

Before designing any flows, I ran a discovery sprint — competitive analysis, user interviews, and behavioral walkthroughs — to understand where OTA discovery breaks down and what conversational AI could uniquely address.

Key Findings

Search is too rigid.

Users want to start with intent ("somewhere warm, boutique, good for remote work") not pre-defined filters. Existing tools force structure before trust is established.

Price comparison is opaque.

6 out of 8 users tested didn't know that direct prices are often equal or lower — they assumed OTAs had the best deals by default.

Loyalty benefits are invisible.

Users who belonged to hotel loyalty programs frequently didn't know how to apply or compare benefits — especially across an unfamiliar property.

Conversation reduces friction.

Prototype testing showed that users spent 40% less time finding a shortlist when they could describe their needs in plain language vs. using form filters.

From vague intent to confident booking

The core design challenge was mapping the messy, nonlinear reality of travel planning onto a reliable, sequential conversational flow — without making it feel like a form disguised as a chat.

In a chat-native product, the words are the interface. I spent as much time on response structure, tone, and information hierarchy as I would on visual components in a traditional product.

What we tried, what we cut

Not every approach made it to the final product. Here are three directions we explored and the rationale behind the decisions.

The product we shipped

The final DirectBooker app in ChatGPT is an opinionated conversational assistant — it asks fewer questions, surfaces more relevant context, and makes direct booking feel like the obviously smarter choice.

Branding & Components