Expedia
distribution through a third-party conversational assistant (app in ChatGPT)
Expedia was one of the first partners of the apps in ChatGPT launched by OpenAI on October 6, 2025, exposing its inventory inside the conversation across six non-EU markets.
Objective
Show up where travelers start planning outside Expedia's own site, by exposing flight, hotel, and destination inventory directly inside a ChatGPT conversation, with live prices and availability.
The deployment
Expedia was one of the first partners of the apps in ChatGPT, launched by OpenAI on October 6, 2025 through the Apps SDK built on the Model Context Protocol. A user logged in to ChatGPT can ask for travel options (hotels, flights, destinations) with dynamic prices and availability, pulled live from Expedia's infrastructure. The app extends Expedia's ChatGPT plugin launched in 2023, one of the first from a travel player. At launch, it is available to logged-in users in six non-EU markets.
Results Proof C
Official Expedia press release and established trade press (Skift, PhocusWire) documenting a multi-market rollout and an OpenAI launch partner status. Proof of scale = multi-market rollout plus a plugin in production since 2023; performance metrics are not public.
How it works
Documented architectureThe stack in detail
- plateforme OpenAI ChatGPT Assistant that hosts the Expedia app; available to logged-in users in six non-EU markets at launch.
- outil OpenAI Apps SDK Development kit for the apps in ChatGPT, launched on October 6, 2025, on which the Expedia app is built.
- outil Model Context Protocol Open protocol on which the Apps SDK is built; connects the conversation to Expedia's inventory.
- infra Infrastructure inventaire et prix Expedia Provides flights, hotels, and destinations with live prices and availability, extending the 2023 ChatGPT plugin.
How it runs, concretely
For ops teams-
1Request in ChatGPT customer
The logged-in user asks for travel options in a ChatGPT conversation.
-
2Expedia app call AI
ChatGPT invokes the Expedia app through the Apps SDK and the Model Context Protocol.
-
3Inventory retrieval AI / data team
The app queries Expedia's infrastructure for live prices and availability.
-
4Display and handover customer
The options are presented in the conversation, with a handover to Expedia to complete the booking.
The user's request in ChatGPT, resolved against Expedia's inventory and prices through the Model Context Protocol. If the MCP connection or the price feed goes down, the app no longer surfaces bookable options.
How your customers perceive this type of use
Sourced studiesLes consommateurs n'acceptent pas les chatbots par defaut : 64% prefereraient que les entreprises n'utilisent pas d'IA dans leur service client (Gartner, 2024) et pres d'un utilisateur sur cinq du service client par IA n'en retire aucun benefice (Qualtrics, 2025). L'acceptation se construit sur trois conditions mesurees par Salesforce : savoir qu'on parle a une IA, pouvoir escalader vers un humain, comprendre la logique de l'agent.
Acceptance conditions
- Etre informe qu'on parle a une IA et non a un humain (pres de 75% le demandent, Salesforce 2024)
- Un chemin d'escalade clair vers un agent humain (45% plus enclins a utiliser l'agent IA, Salesforce 2024)
- Une logique de l'agent clairement expliquee (44% plus enclins, Salesforce 2024)
Red lines
- Rendre l'humain injoignable : c'est la premiere inquietude des consommateurs sur l'IA dans le service client (Gartner 2024) et 50% craignent que l'IA les coupe du contact humain (Qualtrics 2025)
- Remplacer le service client par l'IA sans alternative : 53% envisageraient de partir chez un concurrent (Gartner 2024)
Sources: Salesforce 2024 · Gartner 2024 · Qualtrics 2025
How to replicate
Inference, not sourcedData prerequisites
- inventory and prices exposable via API
- product catalog structured for a third-party assistant
Org prerequisites
- distribution and product team
- ability to publish and maintain an app on a third-party platform
- brand governance outside its own channel
Possible stack
- OpenAI Apps SDK / Model Context Protocol
- real-time connector to the inventory
- user authentication
The plan, step by step
- Step 1Expose inventory, prices, and availability through a clean, stable API.Deliverable: Documented inventory API load-tested
- Step 2Build the MCP connector and the app through the Apps SDK: search, display, handover to the site to complete.Deliverable: Working app in a test environment
- Step 3Handle user authentication and pass the platform's publication review.Deliverable: App validated and published in the allowed markets
- Step 4Launch, track in-chat traffic and handovers to the site.Deliverable: Traffic and conversion dashboard for the new channel
First step: Expose the inventory through a clean API and an MCP connector, then publish an app on the conversational platform where the audience is.
The same pattern, proven in other industries
Etsy
agentic commerce (in-chat checkout through an open protocol)
Hyundai Motor India
conversational commerce and lead-gen agent
IKEA
brand assistant published on a third-party GPT store
Sources
- S1 Expedia in ChatGPT Primary archive pending
- S2 ChatGPT Travel Apps Are Now a Thing - Starting with Booking.com and Expedia Established press archive pending
- S3 ChatGPT brings apps into chat, starting with Expedia and Booking.com Secondary archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.