{"slug":"newday-lifts-generative-ai-agent-assist-accuracy-from-60-to-over-90","url":"https://findausecase.com/use-cases/newday-lifts-generative-ai-agent-assist-accuracy-from-60-to-over-90","title":"NewDay lifts generative AI agent-assist accuracy from 60% to over 90%","description":"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.","company":"NewDay","industry":"Financial Services","country":"United Kingdom","aiCapabilities":["Retrieval-Augmented Generation","Generative AI","Large Language Models"],"technology":["Amazon Bedrock","AWS Fargate","AWS Lambda","Amazon API Gateway","Amazon OpenSearch Serverless","Amazon Cognito","Anthropic Claude 3 Haiku","Snowflake","Amazon CloudWatch","Streamlit","Microsoft Entra ID"],"deployment":"Public Cloud","problemStatement":"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.","solutionApproach":"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.","businessValue":"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.","evidence":{"band":"high"},"sourceUrl":"https://aws.amazon.com/blogs/machine-learning/newday-builds-a-generative-ai-based-customer-service-agent-assist-with-over-90-accuracy","dates":{"publishedAt":"2026-08-16T09:37:55.244Z","publishedAtSource":"ledger","updatedAt":"2026-08-18T13:38:21.439Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/newday-lifts-generative-ai-agent-assist-accuracy-from-60-to-over-90. Bulk republication requires permission."}