Perry Ellis · Yotpo
1.4% — conversion rate
Independently reportedRetail & e-commerce · Customer support · NLP · Scaled
Customer support
State Farm agent offices · EHVA
Vendor-reportedInsuranceUnited StatesScaledEnterpriseNLP
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by ehva.ai (vendor self-report). Checked against the source page on 2026-09-06. 6 of 6 figures below appear on that page word for word.
The problem
Inbound calls constantly interrupted staff, leading to lost productivity, inconsistent customer experience, and no systematic way to log requests across 400 agent offices.
What was deployed
- Vendor
- EHVA
- Products
- EHVA
- Technique
- NLP
- Build or buy
- Bought off the shelf
- Deployment
- SaaS
- Data used
- agency’s knowledge base and account information
- Scale
- 400 State Farm agent offices, 12,000 calls per day
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
91%Callers unaware they spoke with an AI
“91% of callers reported no awareness that they had spoken with an AI.”
Quoted word for word from the source
100%Calls answered without human involvement
“Case Study: State Farm Agencies, 100% of Inbound Calls Handled by EHVA Across 400 Locations”
Quoted word for word from the source
12,000Calls handled per dayper day
“12,000 calls per day handled autonomously across the full deployment, roughly 30 per agency per day with peak-period variance”
Quoted word for word from the source
400Active agency deployments
“400 active deployments, each independently configured for that agency's name, staff, lines of business, and routing preferences”
Quoted word for word from the source
100%Call answer rate
“100% call answer rate across all 400 agencies, zero voicemail during business hours, zero missed after-hours calls”
Quoted word for word from the source
ZeroHold time
“Zero hold time, every call answered on the first ring and handled to resolution or routing without queueing”
Quoted word for word from the source
increasedJob satisfactionafter EHVA was deployed
“every employee reported increased job satisfaction and meaningfully higher productivity after EHVA was deployed.”
Quoted word for word from the source
meaningfully higherProductivityafter EHVA was deployed
“every employee reported increased job satisfaction and meaningfully higher productivity after EHVA was deployed.”
Quoted word for word from the source
“Before EHVA, the phone was running our office. Now our office runs the phone.”
Difficulties and limits
- inbound call volume is constant and unpredictable
- cumulative effect of interruptions across a full day is significant
- no triage, no filtering, and no way to distinguish a routine billing question from a time-sensitive claim call
- consistency problem: Each office was handling calls differently, with different hold times, different voicemail practices, and different levels of after-hours coverage
Sources
- ehva.ai — vendor self-report, 2026-04-21
Similar deployments
Innovative Dining Group · Revmo AI
1200+ — Reservations booked by AI
Vendor-reportedTravel & hospitality · Customer support · NLP · In production · 2025
Houston Methodist · ActiumHealth
18000000 — staffing capacity created
Vendor-reportedHealthcare · Customer support · LLM · In production
Luxury Bath NJPA · Hatch AI
52% — Overall set rate
Vendor-reportedConstruction & real estate · Customer support · AI agents · Scaled
Radiant Credit Union · interface.ai
60% — Asset growth absorbed without contact center team expansion
Vendor-reportedBanking & finance · Customer support · LLM · Scaled · 2022
Talkmobile · LivePerson
92% — Customer Satisfaction Score (CSAT)
Vendor-reportedTelecom · Customer support · NLP · Scaled · 2014