Perry Ellis · Yotpo
1.4% — conversion rate
Independently reportedRetail & e-commerce · Customer support · NLP · Scaled
Customer support
Santander Bank Polska · Softwise.AI
Vendor-reportedBanking & financePolandIn productionEnterpriseNLPLive 2019
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 softwise.ai (vendor self-report). Checked against the source page on 2026-09-05. 5 of 5 figures below appear on that page word for word.
The problem
Nearly 400 customer service consultants had to support an expanded product range and new customer base post-merger, with limited time to absorb changes and fragmented knowledge.
What was deployed
- Vendor
- Softwise.AI
- Products
- AI-powered knowledge assistant, AI Knowledge Assistant, unified knowledge platform
- Technique
- NLP
- Build or buy
- Bought off the shelf
- Deployment
- SaaS
- Data used
- bank's intranet, network drives, and external sources
- Scale
- approximately 300 consultants
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.
97.6correct answersafter a month
“97.6% correct answers after a month of working with the platform.”
Quoted word for word from the source
average conversation time with customers
“7% reduction in average conversation time with customers.”
Quoted word for word from the source
89.7user satisfaction
“89.7% user satisfaction among consultants using the application.”
Quoted word for word from the source
8827queries sent to the assistantin the analyzed period
“8,827 queries sent to the assistant in the analyzed period”
Quoted word for word from the source
97.6intent recognition ratein the analyzed period
“intent recognition on 97.6% of them.”
Quoted word for word from the source
onboarding time
“Faster onboarding for new customer service employees.”
Quoted word for word from the source
complaints
“Fewer complaints as the risk of incorrect answers fell.”
Quoted word for word from the source
second-line dependency
“Lower second-line dependency - a smaller share of calls required escalation to senior consultants.”
Quoted word for word from the source
“The solution was implemented and used by approx. 300 consultants. This allowed us to reduce the number of advisers' inquiries to the Bank support line in a strategic moment, thanks to which the time of conversations was reduced by 7%. In the analyzed period, 8,827 queries were sent to the chatbot, of which 97.6% of the intentions were recognized.”
Difficulties and limits
- Extended response times to customers
- Slow, expensive consultant onboarding
- High employee turnover
- Large thematic specialization across teams
- High dependency on second-line support
- Risk of incorrect answers
Sources
- softwise.ai — vendor self-report, 2025-03-07
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