![case study](https://cdn.quantiphi.com/2024/02/965a4b85-cs_multilingual-virtual-agent-concierge-service.png)
Multilingual Virtual Agent Concierge Service
Public SectorBusiness Impacts
~57,000
Sessions
88+%
Accuracy
~4,000
311 Service Requests Created
Customer Key Facts
- Location : North America
- Size : ~5000 employees
- Industry : Public Sector, Government
Problem Context
The client is one of the top 10 most populous city in the United States, with over 1.3 million residents. On a monthly basis, the City Department receive 300,000 queries from residents in English as well as Spanish. These topics range from 311 requests to COVID assistance as well as information on city service hours.
311 requests, which make up roughly 50,000 requests per month, involve the residents having to create a service request based on their issue type, or check the status of an existing request. Since queries were asked in English and Spanish, representatives had to be trained to handle queries in both languages. This led to increased effort and cost for the city. Additionally, due to restricted contact hours, representatives were unable to respond to resident queries outside business hours and every time a resident was connected to a new representative, they had to repeat the details of their previous conversations.
Providing immediate assistance for urgent queries was a challenge due to the limitations on live agent assistance, especially during the unfortunate pandemic. This led to longer wait times and frustrated residents. Therefore, the client wanted to better address resident queries and reduce the workload of its representatives by transforming the experience of their residents using a Virtual Agent.
Challenges
- Ability to handle queries in multiple languages (English, Spanish)
- As the response to queries keep changing, the solution required the need to update the bot response easily
- Handling complex, dynamic queries like creating 311 requests for different service types
![](https://cdn.quantiphi.com/2024/02/312fa0b5-challenges_multilingual-virtual-agent-concierge-service.png)
Technologies
![Google Cloud Platform](https://cdn.quantiphi.com/2024/02/google-cloud-platform.png)
Google Cloud Platform
![Dialogflow](https://cdn.quantiphi.com/2024/02/6a1ff213-dialogflow-logo.png)
Dialogflow
![GitLab](https://cdn.quantiphi.com/2024/02/gitlab.png)
GitLab
![Node.js](https://cdn.quantiphi.com/2024/02/node.js-2.png)
Node.js
![BigQuery](https://cdn.quantiphi.com/2024/02/da18ec97-bigquery.png)
BigQuery
![Data Studio](https://cdn.quantiphi.com/2024/02/google-data-studio-logo.png)
Data Studio
Solution
Quantiphi built an AI-powered multilingual chat-based Virtual Agent solution, providing immediate assistance to residents and representatives in handling high query volumes and enabling process optimization and cost effectiveness. The virtual agent helps residents create and check the status of their 311 requests, with the capability of addressing more than 150+ service request type queries in English and Spanish. It also provides assistance across other critical use cases, including: COVID assistance, Agency and permit queries, Scheduling of appointments and Customer Service queries, including Library and Department service hours
Result
- 24/7 user support even during non-business hours and public holidays
- ~4000 311 service requests created using the Virtual Agent
- Conversation designed for recognizing nuanced facility and agency names while maintaining seamless user experience
- Solution configuration for instantaneous updates to important queries, including COVID assistance