It support · Production

Agoda's GenAI Journey: 73% Employee Adoption and 204 Applications in Two Years

The problem

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.

Workflow diagram · grounded in source
1
Company-wide GPT Hackathon
Trigger
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.
▾ source quote
“In February 2023, over 200 developers across product and tech came together for a three-day company-wide event to explore one question: What could we build if we put large language models in the hands of our people? Teams were given …”
2
GenAI Proxy centralized gateway
Integration
A GenAI Proxy was built as a centralized access point for all GenAI traffic inside Agoda.
▾ source quote
“A core part of that foundation was our GenAI Proxy, a centralized access point for all GenAI traffic inside Agoda”
3
Internal Chat Assistant Platform
Output
An internal Chat Assistant Platform was launched to give every employee broad access to GenAI-powered chat assistants for everyday tasks.
▾ source quote
“we introduced our internal Chat Assistant Platform (akin to ChatGPT UI Clone) — a cost-effective, secure tool designed to give every employee broad access to GenAI-powered chat assistants for everyday tasks, boosting productivity and shifting mindsets around GenAI adoption”
4
AskGoda auto-answers internal tickets
Ai action
AskGoda supports technical support channels by auto-answering internal questions using documentation and past tickets, handling 50% of incoming tickets.
▾ source quote
“AskGoda supports technical support channels by auto-answering internal questions using documentation and past tickets, reducing load on teams by handling 50% of incoming tickets”
5
Engineering coding agents in IDE
Ai action
Developers use tools like GitHub Copilot, Cursor, Claude Code, and OpenAI Codex as coding agents inside the IDE.
▾ source quote
“Developers have embraced GenAI inside the IDE, using tools like GitHub Copilot, Cursor, Claude Code, OpenAI Codex, and others for coding agents”
6
Customer-facing Q&A Assistants
Output
Q&A Assistants embedded across Agoda help users get quick natural language answers about hotels, policies, or booking form details.
▾ source quote
“Q&A Assistants: embedded across Agoda to help users get quick, natural language answers, whether about hotels, policies, or booking form details — improving clarity and conversion”
Reported 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.

Reported metrics
employee GenAI tool adoption73%
internal tech support tickets handled by GenAI45%
AskGoda incoming ticket handling rate50%
GenAI applications and services deployed by mid-2025204
Show all 9 reported metrics
employee GenAI tool adoption73%
internal tech support tickets handled by GenAI45%
AskGoda incoming ticket handling rate50%
GenAI applications and services deployed by mid-2025204
GenAI applications launched in 2023119
employee GenAI weekly adoption by Q1 2024a third of our employees were using GenAI tools weekly
employee GenAI adoption by Q3 202450%
hackathon prototypes developedMore than 40 ideas were prototyped
customer experience and engagement impactboosting customer experience and engagement
Reported stack
GitHub CopilotCursorClaude CodeOpenAI CodexAskGodaMeeting HelperDocument ProcessorSlackJira
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://medium.com/agoda-engineering/a-retrospective-agodas-genai-journey-thus-far-b0739683d53e
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

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.

What tools did this team use?

GitHub Copilot, Cursor, Claude Code, OpenAI Codex, AskGoda, Meeting Helper, Document Processor, Slack, Jira.

What results were reported?

employee GenAI tool adoption: 73%; internal tech support tickets handled by GenAI: 45%; AskGoda incoming ticket handling rate: 50%; GenAI applications and services deployed by mid-2025: 204 (source-reported, not independently verified).

How is this it support AI workflow structured?

Company-wide GPT Hackathon → GenAI Proxy centralized gateway → Internal Chat Assistant Platform → AskGoda auto-answers internal tickets → Engineering coding agents in IDE → Customer-facing Q&A Assistants.

Related it support cases

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.

Browse the It support cases →