How a US logistics enterprise reduced its customer query resolution time by 95%
A last-mile delivery platform connected Robylon’s AI agents to Freshdesk and had 52% of its tickets resolved automatically within a few minutes, where the average ticket had taken 2-3 hours to resolve.
- > 95%
- Improvement in AHT
- ~52%
- Ticket resolution rate
- Customer
- Logistics provider
- Industry
- Logistics
- Published
- (updated )
Who is the client?
Our client is a delivery management platform that excels in last mile delivery. They provide AI powered tech solutions to 100+ businesses across 25+ countries to ensure on-time, cost effective deliveries.
What was the challenge?
Our client uses Freshdesk to manage the customer support tickets. With a growing customer base, they began receiving a large volume of tickets.
Most of these tickets were repetitive, with similar issues being raised by different clients. Resolving these took most of the bandwidth of the support team. Hence, it was taking on average ~2-3 hours (AHT) to resolve a ticket. Additionally, the priority tickets were also getting queued for a long time.
How did Robylon solve it?
We deployed our AI powered agents and customized it based on the client requirements. The AI agents were integrated with Freshdesk, client’s customer ticketing system.
Our AI agent automatically resolved the repetitive tickets without any manual intervention. About 15% of the resolutions were sent for human verification before responding to the customer.
The process included following 3 steps:
Step 1: Intent Identification from customer query
An intent identification AI agent was created. It was trained on 30k+ historical tickets of the client. Each new incoming ticket was passed to the agent to figure out the intent of the Customer query. (eg. “AWB not generated, User creation failed”)
Step 2: Automated query resolution
Each intent has an AI agent to handle the query, debug it and generate the appropriate response. Within each AI agent, the relevant information was retrieved and actions performed across a variety of platforms used in the Logistics industry.
At the end of the workflow, an appropriate response is generated and sent back to the customer.
Step 3: Query escalation
~15% tickets that scored low on AI confidence level were escalated for human verification before responding to the customer.
What were the results?
Our AI Support agent automatically resolved 52% customer tickets within a few minutes. This helped the human agents focus on resolving the priority tickets.
Our platform seamlessly integrates with customer support softwares like Zendesk, Freshdesk, Zohodesk, etc. Using it, companies can reduce query resolution time by over 90% and save costs by 30%.
