NewDay lifts generative AI agent-assist accuracy from 60% to over 90%
NewDay · United Kingdom
NewDay, whose contact centre handles 2.5 million calls a year, built NewAssist, a generative AI assistant on Amazon Bedrock using Retrieval Augmented Generation, out of an internal hackathon. Through iterative experiments — including a custom parser for its knowledge base and injecting internal acronyms into prompts — NewDay raised NewAssist's accuracy from below 60% to over 90%, cut the average time to retrieve an answer from 90 seconds to 4 seconds, and rolled it out to over 150 agents, running on serverless AWS infrastructure for under $400 a month.
Overview
NewDay, whose contact centre handles 2.5 million calls a year, built NewAssist, a generative AI assistant on Amazon Bedrock using Retrieval Augmented Generation, out of an internal hackathon. Through iterative experiments — including a custom parser for its knowledge base and injecting internal acronyms into prompts — NewDay raised NewAssist's accuracy from below 60% to over 90%, cut the average time to retrieve an answer from 90 seconds to 4 seconds, and rolled it out to over 150 agents, running on serverless AWS infrastructure for under $400 a month.
The challenge
NewDay's contact center handles 2.5 million calls annually, and with nearly 200 knowledge articles in Customer Services alone, agents often needed to search for the right answer to a customer question. This led to a hackathon problem statement in early 2024: how could NewDay harness generative AI to improve speed to resolution and improve both the customer and agent experience.
The solution
Out of the hackathon, NewDay built NewAssist, a real-time generative AI assistant on Amazon Bedrock, implemented as a Retrieval Augmented Generation (RAG) solution. A Streamlit UI hosted on AWS Fargate lets agents log in and ask questions, with authentication via Amazon Cognito and Microsoft Entra ID for single sign-on. Knowledge articles are retrieved via API, chunked with a custom-built parser designed around NewDay's specific content schema, converted to vector embeddings and stored in Amazon OpenSearch Serverless. Suggestions are generated by passing the retrieved chunks to Anthropic's Claude 3 Haiku via Amazon Bedrock. Questions and answers with feedback are logged in Snowflake for observability, and Amazon CloudWatch logs requests processed by the AWS services. New versions are evaluated offline against an evaluation dataset before being promoted to production.
Reported business value
NewDay raised NewAssist's accuracy from below 60% to over 90%, cut the average time to retrieve an answer from 90 seconds to 4 seconds, and rolled it out to over 150 agents, running on serverless AWS infrastructure for under $400 a month.
Sources
Open any source and check the claim yourself — that is the point of the register.
Other financial services entries in the register.
Banking Innovator bunq Supports Growth, Strengthens Security Using AWS
bunq, a Dutch neobank with over 11 million users across Europe, uses Amazon Bedrock for several generative AI use cases including summarizing new user data with large language models, removing the need for agents to process onboarding documents manually. Using Amazon Bedrock, bunq tripled user support process efficiency while maintaining over 90 percent accuracy. Sensitive data stays within bunq's AWS virtual private cloud, supporting GDPR and PCI DSS compliance alongside tools such as AWS CloudHSM, AWS Security Hub and AWS KMS.
TBC Bank Operationalizes Trusted Data with Lakebase
TBC Bank, the largest banking group in the Caucasus region, built a Lakehouse on Databricks and adopted Lakebase and Databricks Apps to move from on-premises SQL Server instances and month-long reporting cycles to self-service analytics and AI-driven applications, including a web-based AI chatbot and AutoML-based credit risk scoring. Credit risk model deployment fell from 14 weeks to two days, and more than 600 users regularly query governed data through Genie.
ING Bank transforming operations through agentic AI
ING Bank is running multiple AI projects across operations, governed centrally under its COO. Live/early-production efforts include a retail chatbot, AI-driven identification of hidden affluent clients for marketing, AI-assisted transaction monitoring that helps investigators close standard alerts faster and focus on risk, and a customer due diligence (KYC) redesign that uses existing public and behavioural data to auto-answer most of a roughly 100-question review, cutting due diligence from days or weeks to seconds. ING is also developing agentic AI to handle mortgage applications end-to-end (credit checks, data collection) starting in 2026. ING's COO said AI introduced to an operations process yields a 25% productivity gain, with freed capacity redeployed to growth and more complex work, and its CTO described 'conservatively aggressive' governance restricting AI exploration to five areas under COO control.
Hyundai Capital America: Transforming customer experience with messaging innovation
Hyundai Capital America (HCA), the finance arm of Hyundai Motor Group for Hyundai, Kia and Genesis leases and loans in the US, partnered with LivePerson starting from a 2018 proof of concept to shift from a voice-dominated contact center to a data-driven, messaging-first strategy across SMS and Apple Messages for Business. Using deflection-to-messaging on high-friction payment interactions, HCA achieved 94% customer satisfaction, an 89% containment rate, and grew messaging engagement from 10,000 to over 100,000 customers served monthly. HCA and LivePerson co-developed a PCI-compliant chatbot debit card payment integration with payment processor ACI.
Was this helpful?
Your feedback helps us improve our use case database