customer_support · finance · workflow
Tilt operationalizes AI customer service across every channel with Ada, achieving 84% automated resolution rate on chat
As Tilt's customer base grew, their support backlog expanded and high staff turnover made hiring and training a persistent challenge; handling roughly 30,000 emails per month, they needed to scale without adding headcount.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Customer initiates authenticated chat
In chat, customers must be logged in, giving the AI agent access to richer, account-level context through various APIs.
Tools used
AdaCoaching and Playbooks
Outcome
Ada's AI agent achieved an 84% automated resolution rate on chat, raised CSAT by 8 points (up to 15 in some cases), reduced email first response time by 9 hours, and reached 94% containment, while generating richer conversational data that the product team uses for strategic decisions.
Results
Volume64%
Grounding & classification
Source type: vendor customer story
23 fields verified against source quotes, 6 dropped as unverifiable.
agentic workflowconversational aisupport agentchat transcriptemailsupport tickethuman review describednamed customertools describedworkflow describedfinancial servicesautomation ratecustomer satisfactiondeflection rateemployee productivityresponse time reductionvendor customer storycustomer supportticket triageautonomous resolutionintake to triage