Customer support · Production

DNB transforms internal customer service operations with Juno, a conversational AI virtual agent for agent-facing knowledge access

The problem

DNB's customer service agents and banking advisors faced delays in assisting customers because the previous document management system required them to manually search for routines, making it inefficient and time-consuming.

Workflow diagram · grounded in source

Agent opens Juno chatbot

trigger

“In March 2020, DNB launched the virtual agent Juno to assist its agents and advisors in quickly and easily accessing the various routines they need to follow when assisting customers”

Welcome message with system status

output

“Upon opening the chatbot, agents are greeted with a welcome message that informs them of the status of the bank's various services and any recent changes made to routines”

Department-specific filtering

routing

“Filtering enables Juno to tailor its replies so that agents each receive a unique, department-specific response, instead of a generic one”

Routine and topic answer delivery

ai_action

“Juno can answer questions on more than 3,400 topics, with each of these then further customized towards seven different areas within the bank”

Automated system status check

integration

“Juno can automatically check the status of different systems within the bank and inform agents of any issues or disruptions so that they can better assist customers”

Continuous improvement via data mining

feedback_loop

“the AI trainers who maintain Juno are able to mine this data, identifying areas that require updates and ensuring continuous improvement of the chatbot's performance”

Reported outcome

Juno replaced the previous data management system entirely and became the exclusive tool for agents to access routines, reaching 1,200 daily active users, 80,000 conversations per month, and over 2 million questions answered in 2022.

Reported metrics

Daily active users1,200

Conversations per month80,000

Questions answered in 2022over 2 million

topics covered by Junomore than 3,400

Show all 6 reported metrics

daily active users1,200

conversations per month80,000

questions answered in 2022over 2 million

topics covered by Junomore than 3,400

incoming chat traffic automated by Ainoover 50%

agent information access speedmore quickly and effectively than ever

Reported stack

boost.aiJunoAPIsrobotic process automation (RPA) systems

Source

https://www.boost.ai/case-studies/how-dnb-transformed-customer-service-operations-and-enhanced-human-agent-efficiency-with-conversational-ai

Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Juno replaced the previous data management system entirely and became the exclusive tool for agents to access routines, reaching 1,200 daily active users, 80,000 conversations per month, and over 2 million questions a…

What tools did this team use?

boost.ai, Juno, APIs, robotic process automation (RPA) systems.

What results were reported?

Daily active users: 1,200; Conversations per month: 80,000; Questions answered in 2022: over 2 million; topics covered by Juno: more than 3,400 (source-reported, not independently verified).

How is this customer support AI workflow structured?

Agent opens Juno chatbot → Welcome message with system status → Department-specific filtering → Routine and topic answer delivery → Automated system status check → Continuous improvement via data mining.