Customer support · Production

Cebu Pacific replaces scripted chatbot with Ada's generative AI agent, achieving 34%+ higher automated resolution rate and 50%+ higher CSAT

The problem

Cebu Pacific's scripted chatbot Charlie lacked personalization, required heavy manual effort to maintain flows and integrations, and could only answer the latest question in a conversation without retaining context.

First attempt

The declarative scripted chatbot approach required constant manual effort — hardcoding flows, uploading content manually, and line-by-line data reviews — and could not understand conversation context or deliver personalized responses.

Workflow diagram · grounded in source
1
Customer sends chat inquiry
trigger
“customers can access via the airline's website, mobile app, or Facebook page”
2
AI agent answers from knowledge base
ai_action
“Charlie now pulls answers directly from Cebu Pacific's robust knowledge base, eliminating the need to hardcode flows or upload content manually. The AI agent delivers contextual responses, can link customers to relevant resources, and ha…”
3
Triage and priority routing
routing
“With Ada's AI agent triaging inquiries and collaborating with Salesforce routing, Cebu Pacific was able to implement this prioritization effectively, ensuring the right issues were escalated at the right time.”
4
Escalation handover with summary
human_review
“When Charlie escalates a conversation, agents receive a summary of the exchange, allowing them to pick up where the AI left off. This reduced both handling time and the need for customers to repeat themselves”
5
Continuous AI coaching and monitoring
feedback_loop
“By using Ada's AI agent coaching capabilities, the customer care team provides targeted guidance to ensure the AI agent delivers accurate, compliant responses. On the backend, the team uses Ada's platform to monitor key performance metri…”
Reported outcome

After deploying Ada's generative AI agent, Cebu Pacific achieved a 34%+ higher automated resolution rate and 50%+ higher CSAT scores, with wait times for high-priority disruption cases reduced to under one minute.

Reported stack
AdaAda AcademySalesforce
Source
https://www.ada.cx/case-study/cebu-pacific
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

After deploying Ada's generative AI agent, Cebu Pacific achieved a 34%+ higher automated resolution rate and 50%+ higher CSAT scores, with wait times for high-priority disruption cases reduced to under one minute.

What tools did this team use?

Ada, Ada Academy, Salesforce.

What failed first in this deployment?

The declarative scripted chatbot approach required constant manual effort — hardcoding flows, uploading content manually, and line-by-line data reviews — and could not understand conversation context or deliver person…

How is this customer support AI workflow structured?

Customer sends chat inquiry → AI agent answers from knowledge base → Triage and priority routing → Escalation handover with summary → Continuous AI coaching and monitoring.

Related customer support cases