Document Processing
Regis Aged Care needed to compress a daily clinical handover review that could take two to three hours for 200-plus pages of notes, without missing a single resident-level clinical signal.
Reported impact
Regis reduced handover review time from hours to under an hour, expanded the assistant from a two-home proof of concept into production across its network, and redirected clinician time toward resident care while maintaining strict safety standards.
Cognizant and Regis Aged Care built a generative AI assistant to compress daily handover review without losing key resident detail. The solution ingests more than 200 pages of clinical progress notes, processes them in segments, and reassembles the results through a custom prompt that produces structured summaries for each resident and answers ad hoc questions in a familiar chat interface. The proof of concept ran in two homes on Microsoft Copilot Studio with the authentication and security controls required for healthcare, then moved into full production across the Regis network after benchmarking against a registered-nurse baseline. Cognizant and Regis continue to tune the assistant against categories such as agitation, medication and infection, while change-management work helps clinicians adopt the tool as support rather than replacement. The design combines note ingestion, prompt orchestration, benchmarking and human trust-building so review time falls without compromising safety.
Clinical progress notes are ingested, segmented for model processing, and then reassembled through a custom prompt that creates resident summaries and answers questions in a chat interface. Clinician-defined benchmarking compares the output with control answers and registered-nurse results, while production staff use the assistant in routine handovers across the Regis network.
“Beginning with a proof of concept in two Regis homes, a trial was conducted with a solution built on Microsoft Copilot Studio with the authentication and security controls required for a healthcare environment.”
“Nearly 60% of staff are now frequent users, utilizing the tool daily or several times a week.”
“The collaborative process was essential for designing and delivering a clinically trustworthy generative AI assistant that ingests clinical progress notes, produces structured summaries for each resident and answers both standard and ad hoc queries through a familiar chat interface.”
“The techniques used ensured the model could process the material in segments while never losing the thread of information”
“no hallucinations occurred across the trials and accuracy of note review was the same or better than the registered nurse baseline on the majority of clinical note categories”
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.
Regis prides itself on providing high quality care and services through its team of over 13,000 dedicated nurses, carers, and support professionals.
Related
Google Cloud Sample Archived · Oct 9, 2026 Angelus Founded by a dentist whose first product was based on a patent, Angelus competes on differentiation, developing bioceramic products and fiberglass post lines that require clinical proof, intellectual property… 50,000 pages of proprietary data now powering AI-generated documents Gemini Google Cloud Sample Archived · Aug 5, 2026 DeepHealth DeepHealth needed to handle rising imaging volumes, a worsening radiologist shortage, and the need to deliver faster, more consistent cancer detection without limiting access to high-quality diagnostics to major urban… 20M+ medical images streamed yearly with Cloud Healthcare API BigQuery · Cloud Healthcare API · Gemini 
In-house Sample Jul 28, 2026 Novartis Novartis R&D needs to turn large volumes of scientific, clinical, operational, and real-world data into faster, higher-quality decisions across drug discovery and development, reducing cycle times, surfacing safety… less than 10 percent of drug candidates historically reach the market AI models · AI-enhanced analytics · Generative AI 
