Enterprise Knowledge Search
NatWest Group wanted colleagues to get faster, more efficient support for workplace and HR queries while reducing the load on human support teams for routine questions.
Reported impact
The Gen AI enhancement gives colleagues quicker, easier access to HR information through more natural conversations and more targeted answers, while allowing human agents to spend more time on complex support cases.
NatWest Group deployed generative AI into its internal virtual colleague chatbot, Ask Archie, to improve how employees get support for workplace and HR questions. Ask Archie acts as the serving layer for a 24/7 conversational interface, while the Gen AI capability makes exchanges more natural and improves answer targeting for colleague questions. The implementation is grounded in NatWest's existing knowledge bases plus specific HR documents and policies, which function as the underlying information sources the chatbot surfaces to users. When a query is within scope, Archie returns targeted answers and links to the relevant policy content; when it cannot resolve a question, the workflow hands the case to a human colleague for further assistance. The initial rollout focuses on family-related HR policies such as adoption leave, partner leave, and shared parental leave, with NatWest planning to expand the knowledge coverage over time.
NatWest colleagues submit workplace and HR questions to Ask Archie. The chatbot uses generative AI to conduct more natural conversations and draw on NatWest knowledge bases plus HR policy documents to return targeted answers and links to relevant content. If Archie cannot answer, the request is handed to a human colleague or agent for further support. The initial knowledge scope covers family-focused HR policies, with more content planned over time.
"Ask Archie is our 24/7 artificial intelligence chatbot who answers some of our colleagues most frequently asked questions on a range of topics."
"Ask Archie's Gen AI capabilities create better, more natural conversations and share more targeted information and links to specific documents and policies."
"By using Generative AI, we're helping our virtual colleague chatbot Ask Archie to provide more targeted answers to colleague questions."
"We're harnessing the latest technology to help our colleagues get answers to their HR queries quicker and more efficiently."
"When Archie can't answer a question, he brings in one of our colleagues to assist further."
"groundbreaking work that gives colleagues conversational access to our knowledge bases for the first time."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
For more information, or to submit a proposal please write to our head office: Head of Sponsorship, NatWest Group plc, 1st Floor, House F, Gogarburn, Edinburgh, United Kingdom, EH12 1HQ.
By taking the best of that learning and making it available to all 60,000 colleagues across the group, this structured programme is designed to embed critical skills across the organisation.
Related
In-house Sample Apr 23, 2026 PayPal PayPal needed to give employees conversational access to company data at enterprise scale without requiring SQL, dashboards, or intermediary engineering teams, while still meeting strict security and compliance… answers in minutes instead of hours Looker · MCP In-house Sample Sep 30, 2025 Bank of America Global Payments Solutions employees needed too long to answer complex client product and onboarding questions because knowledge was spread across internal materials and often required calls with product specialists in… more than 40,000 business clients worldwide Ask Global Payments Solutions (AskGPS) In-house Sample May 26, 2025 BNP Paribas BNP Paribas must design and distribute investment products tailored to each retail customer while handling very large volumes of information, complying with stringent regulation, and giving advisers and customers clear… several billion possible combinations algorithm · automated preparation of performance reports · internal conversational assistants 