Customer support · Production

Borrowell achieves 83% AI resolution rate powering Zendesk ticketing with Tidio Lyro AI Agent

The problem

Borrowell's nine-agent support team was managing over 11,000 tickets per month—with peaks beyond 12,000—and needed a way to scale support without increasing headcount as the business continued to grow.

Workflow diagram · grounded in source
1
Member initiates support chat
trigger
“introduced Tidio's Lyro AI to handle conversations before they turned into tickets”
2
Lyro AI answers from knowledge base
ai_action
“AI-powered question answering for common customer inquiries. Lyro is trained on Borrowell's Zendesk help center articles. Continuous updates: easy refresh of the knowledge base whenever help center content changes. Manual training: abili…”
3
Unresolved: ticket created in Zendesk
integration
“Conversations Lyro can't resolve are automatically converted into Zendesk tickets. Full chat transcripts are included in every ticket. Member contact details are collected during the conversation”
4
Ticket routed to support queue
routing
“Tickets are routed to the appropriate support queues”
5
Agent handles complex case
human_review
“allows agents to spend more time on complex issues that require human judgment and personal attention”
6
Unanswered questions reviewed
feedback_loop
“Reviews unanswered questions and adds new responses”
Reported outcome

Lyro AI achieved an 83% resolution rate and 87% answer rate, deflecting repetitive tickets so agents could focus on complex issues requiring human judgment while providing members with 24/7 support.

Reported metrics
Answer rate87%
Help center engagement rate65%
Monthly ticket volume baselinemore than 11,000 tickets per month
Monthly ticket volume peakbeyond 12,000 per month
Show all 7 reported metrics
answer rate87%
help center engagement rate65%
monthly ticket volume baselinemore than 11,000 tickets per month
monthly ticket volume peakbeyond 12,000 per month
support team sizenine agents
ticket volume deflectionreduces incoming ticket volume
support costsDeflecting simple tickets helps keep costs under control
Reported stack
LyroZendesk
Source
https://www.tidio.com/customers/borrowell/
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Lyro AI achieved an 83% resolution rate and 87% answer rate, deflecting repetitive tickets so agents could focus on complex issues requiring human judgment while providing members with 24/7 support.

What tools did this team use?

Lyro, Zendesk.

What results were reported?

Answer rate: 87%; Help center engagement rate: 65%; Monthly ticket volume baseline: more than 11,000 tickets per month; Monthly ticket volume peak: beyond 12,000 per month (source-reported, not independently verified).

How is this customer support AI workflow structured?

Member initiates support chat → Lyro AI answers from knowledge base → Unresolved: ticket created in Zendesk → Ticket routed to support queue → Agent handles complex case → Unanswered questions reviewed.

Related customer support cases