Normalized claim
Hours saved per month per customer service employee: 100 hours/month/employee increase
saving more than 100 hours a month per customer service employee
GCPEvidence: Medium50/100
Nanyang Technological University (NTU Singapore): Dialogflow CX + Gemini chatbot saving 100+ hours/month
Use case typeStudent support assistantUpdated Apr 17, 2024
Nanyang Technological University, Singapore (NTU Singapore) sought more advanced generative AI solutions to improve its housing chatbot for students and staff. The university built a next-generation Lyon Housing chatbot using Dialogflow CX and Gemini to improve query coverage, cleanse and evaluate historical data, and route complex cases to human agents.
- Organization
- Nanyang Technological University
- Industry
- Education
- Location
- Singapore
- Published
- April 2024
Reported outcomes
2,500 queries/month
queries handled per monthAutomation & deflection
100 hours/month/employeehours saved per month per customer service employee+80%bot answer rate
Strategic outcomes
Speed & agilityImproved student service responsivenessEmployee experienceReduced manual chatbot maintenance effortCustomer experience & trustBetter handling of evolving housing questions
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Queries handled per month: 2,500 queries/month increase
Increases capacity to handle ~2,500 queries a month
Normalized claim
Bot answer rate: 80% increase
The chatbot can fetch answers to more than 80% of queries
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Nanyang Technological University, NTU Singapore
- Provider
- GCP
- Maturity
- Unknown
- Linked source
- Google Cloud Customer Story
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1Student support assistant
- 2Customer service automation
- 3Knowledge management
- The legacy intent-based chatbot required heavy manual effort to update intents and classify queries.
- Housing queries needed better automation and coverage for students and staff.
- Developed a conversational flow for the Lyon Housing chatbot with intent detection, query rewriting, persona classification, and response generation.
- Leveraged Dialogflow CX and Gemini LLMs to improve query coverage and engagement quality.
- Used chatbot data to cleanse and evaluate historical and incoming queries, surfacing actionable insights for further improvements.
Technologies
- The workforce handling housing queries saves more than 100 hours per month.
- The chatbot handles about 2,500 queries monthly and answers more than 80% of them.
- Complex cases are escalated to human agents, improving service continuity.
Architecture
NTU Singapore's Lyon Housing chatbot uses Dialogflow CX and Gemini to perform intent detection, query rewriting, persona classification, and response generation. It also cleanses and evaluates data from historical and live queries while escalating unanswered questions to human agents.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Apr 17, 2024Publisher: Google CloudEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.