it_support · travel · workflow
Agoda's GenAI Journey: 73% Employee Adoption and 204 Applications in Two Years
As Agoda's GenAI experimentation scaled, it faced challenges of governance, cost management, and preventing duplicated effort, while also needing infrastructure to bridge the gap from demos to reliable production applications.
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 · Company-wide GPT Hackathon
In February 2023, over 200 developers came together for a three-day company-wide event to explore what they could build with large language models.
Tools used
GitHub CopilotCursorClaude CodeOpenAI CodexAskGodaMeeting HelperDocument ProcessorSlackJira
Outcome
By mid-2025, 73% of Agoda employees use GenAI productivity tools, 45% of internal tech support tickets are handled by GenAI on average, and 204 applications and services have been deployed across the company.
Results
Time saveda third of our employees were using GenAI tools weekly
Volume73%
Running sinceFebruary 2023
Source
https://medium.com/agoda-engineering/a-retrospective-agodas-genai-journey-thus-far-b0739683d53e
Grounding & classification
Source type: technical build writeup
51 fields verified against source quotes, 2 dropped as unverifiable.
agentic workflowanomaly detectioncode generationcontent generationconversational airagsummarizationsupport agentcode diff prknowledge basemeeting recordingsupport ticketbuilder submittedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedhospitalitytravelautomation ratedeflection rateemployee productivitythroughput increasetechnical build writeupcustomer supportit supportmarketing opsquality assuranceticket triageagentic task executionautonomous resolutionrag answering