Customer support · Production

Forethought Solve helps Spordle deflect 21,000 chat inquiries at an 86% self-serve rate

The problem

Spordle's small support team could not handle cyclical peak-season ticket volumes reaching nearly 7,000 per month, forcing seven or eight additional employees to work as full-time support agents on top of their normal responsibilities, often for 14+ hour days. Daily volumes ranged from 350 to 600+ tickets, with customers waiting through a two-week backlog.

Workflow diagram · grounded in source
1
Customer initiates chat
trigger
“Spordle uses Forethought Solve as its chat widget”
2
AI generates response
ai_action
“Solve uses generative AI to automatically serve up accurate, human-like responses to chat inquiries. Solve's generative AI models are automatically trained on Spordle's data, allowing it to comprehend sentence structure, meaning, and ton…”
3
Bilingual language routing
routing
“the chat widget switches seamlessly between providing responses in French and English”
4
Intent detection via Workflow Builder
ai_action
“With Workflow Builder, built-in generative AI enables Spordle's support team to build automated workflows that detect customer intent to enable seamless self-service”
5
Self-service resolution delivered
output
“Spordle has deflected 21,000 chat inquiries, with an 86% self-serve rate”
Reported outcome

Since March 1, 2023, Spordle deflected 21,000 chat inquiries at an 86% self-serve rate.
Over 600 tickets were instantly resolved within the first week after implementation, and three months post-implementation the ROI reached 142%. Agents are no longer exhausted from dealing with heavy ticket volumes.

Reported metrics
chat deflections since March 202321,000
Self-serve rate86%
ROI at 3 months post-implementation142%
Tickets instantly resolved in first week600+
Show all 9 reported metrics
chat deflections since March 202321,000
self-serve rate86%
ROI at 3 months post-implementation142%
tickets instantly resolved in first week600+
peak monthly ticket volume (pre-implementation)nearly 7000
daily ticket volume range (pre-implementation)between 350 and 600+ tickets per day
overflow employees working as agents (pre-implementation)seven or eight
daily hours worked during peak overflow14+ hour days
ticket backlog duration (pre-implementation)two-week backlog
Reported stack
Forethought SolveWorkflow BuilderForethought
Source
https://forethought.ai/case-studies/spordle
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Since March 1, 2023, Spordle deflected 21,000 chat inquiries at an 86% self-serve rate.

What tools did this team use?

Forethought Solve, Workflow Builder, Forethought.

What results were reported?

chat deflections since March 2023: 21,000; Self-serve rate: 86%; ROI at 3 months post-implementation: 142%; Tickets instantly resolved in first week: 600+ (source-reported, not independently verified).

How is this customer support AI workflow structured?

Customer initiates chat → AI generates response → Bilingual language routing → Intent detection via Workflow Builder → Self-service resolution delivered.

Related customer support cases