Customer support · Production

DNB automates over 50% of chat traffic with boost.ai virtual banking agent Aino

The problem

DNB faced an ever-increasing volume of incoming chat traffic requiring part-time temporary workers, with no scalable way to free staff from repetitive work while providing always-available customer support.

Workflow diagram · grounded in source
1
Customer traffic routed to Aino first
Routing
DNB routes all customer service traffic through the virtual agent first before customers are able to reach human support.
▾ source quote
“routing all customer service traffic to its website through the virtual agent first before customers are able to reach human support”
2
NLU identifies and resolves queries
Ai action
Boost.ai's advanced Natural Language Understanding (NLU) allows Aino to identify what it can and cannot answer, automating thousands of questions daily.
▾ source quote
“boost.ai's advanced Natural Language Understanding (NLU) allows Aino to identify what it can and cannot answer, automating thousands of questions daily”
3
Complex queries routed to humans
Routing
More complex interactions are seamlessly routed to human colleagues when required.
▾ source quote
“seamlessly routing more complex interactions to its human colleagues when required”
4
AI Trainers improve bot responses
Feedback loop
Fifteen full-time AI Trainers are dedicated to training each bot how to best respond to customers and employees.
▾ source quote
“15 full-time AI Trainers working across its suite of virtual agents. Dedicated to training each bot how to best respond to customers and employees”
Reported outcome

Within six months, Aino automated over 50% of all incoming chat traffic and has since interacted with over a million customers.
CSAT scores hit an all-time high of 68% in Q3 2020. By 2021, chat automation reached 55% of all chat traffic.

Reported metrics
Relevant topics covered from day one2,500
Time to production-ready virtual agent8 weeks
Fully-automated daily customer interactions10,000+
Incoming chat traffic automated in 6 monthsover 50%
Show all 12 reported metrics
relevant topics covered from day one2,500
time to production-ready virtual agent8 weeks
fully-automated daily customer interactions10,000+
incoming chat traffic automated in 6 monthsover 50%
customer service traffic automated in 6 months20%
CSAT score Q3 202068%
chat traffic automation range50-60%
total customer service traffic automation across all channels~22%
customers interacted with Ainoover a million
Juno daily usersover 5,000
Juno accuracy rate80%
full-time AI Trainers15
Reported stack
boost.aiNLUAinoJuno
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://www.boost.ai/case-studies/ai-chatbot-banking
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Within six months, Aino automated over 50% of all incoming chat traffic and has since interacted with over a million customers.

What tools did this team use?

boost.ai, NLU, Aino, Juno.

What results were reported?

Relevant topics covered from day one: 2,500; Time to production-ready virtual agent: 8 weeks; Fully-automated daily customer interactions: 10,000+; Incoming chat traffic automated in 6 months: over 50% (source-reported, not independently verified).

How is this customer support AI workflow structured?

Customer traffic routed to Aino first → NLU identifies and resolves queries → Complex queries routed to humans → AI Trainers improve bot responses.

Related customer support cases

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.

Browse the Customer support cases →