Airia
A Conversational AI Search Assistant, helping users find their perfect stay through natural, intuitive conversations. Airia takes in user descriptions and translates them into precise, tailored property recommendations making property discovery seamless and personalized on Airbnb.
Problem Statement
How might we improve user retention and accelerate bookings by leveraging AI to deliver faster, smarter, and proximity-driven search experiences on Airbnb?
Problem Background
The current search experience on Airbnb is overwhelming and inefficient for users due to the extensive number of listings and the complexity of filter-based navigation. Many users struggle to translate their ideal stay into specific search criteria, often adjusting filters multiple times or abandoning their search altogether. As a result, users experience frustration, delayed booking decisions, and a staggering 50% drop-off from the platform. There is an untapped opportunity for Airbnb to utilize GenAI to elevate the search experience for its users which can position Airbnb as the “go-to” platform for a perfect stay any day, anywhere, and anytime.
Research Insights
The research process involved a combination of qualitative and quantitative methods. All participants were Airbnb users that use or have used the platform to book a stay for different purposes in varying capacities. Users spanned across frequent business/work travelers, casual explorers, and occasional vacation goers based in the USA and Canada.
User Pain Points
Ten (10) users were interviewed to gather qualitative data and gain more in-depth insights into the search experience, user frustrations, and preferences; in addition to the 40+ respondents on a distributed survey to gather quantitative data.
The research uncovered that:
- The integrated map on Airbnb is essential for users to tailor their location search. This feature is both a necessity and pain to the user due to its inaccuracy.
- Reviews on property listings trump ratings as a deciding factor.
- A frustrating part of the search process is when listings that are not available are included in the options shown to users. This should not be the case as the filters are there for a reason.
- Safety of both the environment/location and property itself is of utmost importance to users.
- There were mixed sentiments shared about the number of listings shown to users. Some loved it as an exploration while others disliked it as it made the search process overwhelming and caused decision fatigue.
Supporting Data
63% of surveyed travelers prioritize proximity to Points of Interest (POIs) like offices, restaurants, and transit hubs i.e. they are very location-sensitive and Airbnb does not accommodate this type of proximity-based search.
47% regularly switch between Airbnb and Google Maps to verify location details due to a lack of reliable relative distance data on Airbnb. 6 out of 10 users clearly voiced their frustrations with having to switch between two platforms just to confirm a stay. Sentiments like Airbnb having a collaboration/partnership with Google Maps just to improve the accuracy of the current map offering was shared directly from users.
See research findings and user survey verbatims here
Feedback
My preliminary user research to validate this problem provided valuable context for identifying the most critical areas for improvement in the Airbnb search experience as participants had different needs and preferences.
Landing on the Solution
The persona of focus for Airia AI is the High-Flying Business Traveler. This persona is one that travels frequently (2 - 6 trips/month) and is a recurring Airbnb user. They represent a highly valuable cross-segment as solving for them also resolves other identified personas’ major pain points.
With this in mind, the following features were identified to resolve their key user pain points of location accuracy and proximity-driven search on Airbnb:
- Conversational AI Chat Interface → Enabling search through natural language.
- Smart Map + Points of Interest (POI) Pinning → The ability to visualize proximity to preferred spots, see estimated walk times, and explore clusters of relevant listings.
- Preference-Based Filtering → Selecting what truly matters based on preferences
- Booking Support Flow Integrated in Airia’s Chat UI → Minimizing friction points and accommodating a search-to-book completion all in the chat.
- Safe, Privacy-Friendly Map Results (very critical) → Approximating location distances without revealing exact addresses to be compliant with Airbnb’s host privacy standards
Explanation of Solution
Airia is an AI-powered conversational assistant built to enhance the Airbnb search experience by helping travelers quickly find the right place to stay near where they need to be. Instead of relying on traditional filters and static maps, Airia uses natural, chat-based interactions to understand what matters most to each user.
Whether it’s proximity to a conference, a favorite café, or a quiet, work-friendly neighborhood. It integrates an interactive smart map with customizable points of interest, offers curated, proximity-aware stay recommendations, and simplifies decision-making for travelers. By reducing the friction of endless scrolling and uncertainty around location, Airia drives faster bookings, improves user confidence, and ultimately increases retention and revenue for Airbnb.
User Flows
Sample Mockups
For full mobile and desktop experience mockups, click her
Product Assets
Learnings
Product Manager Learnings:
Chikodili Odinakachukwu
1️⃣ Do not begin with a solution in mind. Let the data lead and guide your decisions.
2️⃣ Build for the user. Build for real people and solve real problems.
3️⃣ Most importantly, prioritize with intention and evidence (data! data!! data!!!)
📌 Bonus Learning → Always, always solve a real pain.
Designer Learnings:
Designer Learnings:
Jo Sturdivant
- Adapting to an Established Team: Joining the team in week 6 of 8 was challenging, as I had to quickly adapt to existing workflows, dynamics, and goals. This mirrors real-world situations where you often integrate into teams mid-project, and flexibility is essential.
- Work-Blocking for Efficiency: With only two weeks to complete the project, I learned the importance of a structured work-blocking system. This approach allowed me to manage my time effectively and meet deadlines under pressure.
- Making Data-Driven Design Decisions: Unlike my past projects, I had to rely on research conducted by others. This was a valuable experience in using pre-existing data to guide design decisions, helping me focus on the core insights without starting from scratch.
Developer Learnings:
Developer Learnings:
Vanady Beard
&
As the back-end developer, I learned how important it is to create efficient and reliable systems that support the entire application. This experience also taught me the importance of optimising the database and ensuring the backend is scalable and easy to maintain.
Developer Learnings:
Stephen Asiedu
&
As a back-end developer, I've come to understand the importance of being familiar with various database systems and modules. This knowledge enables me to build diverse applications and maintain versatility in my work. I've also learned that the responsibility for making the right choices rests on my shoulders, guided by my best judgement.
Developer Learnings:
&
Developer Learnings:
Maurquise Williams
&
- Process of Creating an MVP: Developing a Minimum Viable Product (MVP) taught me how to focus on delivering core functionalities balancing between essential features and avoiding scope creep.
- Collaboration in a Real-World Tech Setting: This experience taught me how to collaborate efficiently in a fast-paced tech environment, keeping the team aligned and productive, even while working remotely across time zones.
- Sharpening Critical Thinking and Problem-Solving Skills: This experience honed my ability to think critically and solve problems efficiently. By tackling challenges and finding quick solutions, I sharpened my decision-making and troubleshooting skills in a dynamic, real-world setting.
Developer Learnings:
Jeremiah Williams
&
All in all this experience was very awesome I learned that in coding with others being transparent is key
Developers Learnings:
Justin Farley
&
I learned how important communication is when working with a team. Communication provides understanding, advice, ideas, and much more. While working with the product team, I’ve found that communication keeps everything flowing smoothly. Working with a team also showed me that every member brings something different to the table and we all have to work together in order to align and meet our end goal.