Customer Service Automation · Enterprise Knowledge Search
UHCW NHS Trust needed a more efficient way to answer routine HR and workforce questions for more than ten thousand employees so specialist staff could spend less time on inbox and phone traffic and more time on complex support work.
Reported impact
The Trust created a scalable employee-support channel, reduced the burden on HR teams, and improved access to policy guidance in a way that supports retention, efficiency and better patient-care operations indirectly.
UHCW NHS Trust worked with IBM and SCC on a proof-of-concept called People Assist that combines IBM watsonx Assistant with IBM watsonx.ai to provide 24x7 workforce self-service. Watsonx Assistant delivers the employee-facing interface, while watsonx.ai performs retrieval-augmented generation over HR policy documentation so the assistant can summarize relevant guidance and return answers to common questions. The tool acts as a one-stop shop for policy lookups and routine transactional support instead of forcing staff to wait on email queues or office hours. Because the system is grounded in the Trust's own documentation, it improves consistency as well as speed, and it creates a reusable pattern for future HR automation beyond the pilot. In architectural terms, People Assist sits between users and policy content, using RAG to transform static documents into an interactive service layer for the workforce function.
Employees submit HR questions to People Assist, watsonx Assistant routes the request, watsonx.ai retrieves and summarizes relevant Trust policy documentation with RAG, and the response is returned through the self-service interface at any time of day.
"Almost 50 users accessed People Assist over the weekend or outside core office hours."
"Estimated to save approximately 2,080 working days per year"
"Over 550 conversations on the platform since launch"
"This AI tool, called People Assist, can serve as a one-stop-shop for all HR queries and routine tasks around the clock."
"uses retrieval-augmented generation (RAG) to summarize its findings"
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.
Related
Databricks Sample May 14, 2026 Premier As one of the leading healthcare improvement companies in the U.S., Premier’s mission is to improve community health by enabling better, smarter, and faster healthcare for providers. Serving two out of every three U.S. 30%+ Improvement in analytics project ad-hoc development in the advisory group Databricks Assistant · Databricks Genie · Databricks SQL 
IBM Sample Feb 11, 2025 DI Square DI Square needed to improve call-center operator productivity and reduce dependence on individual know-how as labor shortages and higher staffing costs made it harder to hire, train, and retain operators. IBM Granite · IBM Watson Discovery · IBM watsonx Assistant IBM Sample Jan 6, 2025 IRCEM Group IRCEM needed to answer growing volumes of customer questions about complex pension, insurance, and social-protection topics without forcing advisors to handle every inquiry manually by email or phone. 4,000 conversations per month IBM Cloud Expert Labs · IBM watsonx Assistant 