customer_support · travel · workflow
Automation Platform v2: Improving conversational AI at Airbnb
Airbnb's v1 conversational AI platform relied on rigid, predefined step-by-step workflows that were not flexible enough for diverse customer scenarios and required product creators to manually build new workflows for every use case, making scaling time-consuming and error prone.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User inquiry triggers platform
A user inquiry arrives at the platform, which collects relevant contextual information such as previous chat history, user ID, and user role.
Tools used
Automation PlatformChain of ThoughtLLM
Outcome
Automation Platform v2 enables developers to build LLM applications that help customer support agents work more efficiently, provide better resolutions, and deliver quicker responses, by combining LLMs with traditional workflows.
What failed first
Automation Platform v1's fixed workflow model was too rigid for emerging LLM use cases, and LLM-powered applications themselves are not yet fully production-ready for all of Airbnb's scale due to latency and hallucination concerns.
Grounding & classification
Source type: technical build writeup
27 fields verified against source quotes.
agentic workflowai agentchatbotconversational aiknowledge searchchat transcriptknowledge basefailure mode describednamed customerproduction runtime claimedtools describedworkflow describedhospitalitytravelaccuracy improvementemployee productivityresponse time reductiontechnical build writeupcustomer supportagentic task executionautonomous resolution