Real-time Analytics
Benete needed a way to turn large volumes of BeneCare assisted-daily-living sensor data into usable caregiver insights without forcing nurses and care teams to manually interpret dashboards and create summaries.
Reported impact
Benete gave caregivers near-instant, multilingual summaries of client conditions, sharply reduced the time needed to interpret patient data, and improved the ability to deliver preventive care while serving more elderly clients efficiently.
Benete worked with IBM Client Engineering to add an LLM-based summarization layer to its BeneCare elder-care platform. IoT sensors already captured activity, movement, sleep, hygiene, and food-preparation signals for elderly clients; IBM watsonx.ai was introduced to convert that raw operational data into concise care summaries and multilingual reports. Benete created prompt templates in watsonx.ai, used IBM Cloudant to store structured sensor findings and generated summaries, and tracked model development with Jupyter Notebook plus AI factsheets in IBM watsonx.governance. Llama and Mistral models were evaluated and then deployed on watsonx.ai as endpoints that transform the incoming care data into readable insights integrated back into BeneCare. This architecture preserves the continuous monitoring workflow while automating the most time-consuming interpretation step for caregivers.
IoT sensors feed BeneCare with assisted-daily-living data, Benete stores structured findings in IBM Cloudant, prompt templates in IBM watsonx.ai call Llama or Mistral endpoints to generate summaries and translations, and the resulting outputs are pushed back into BeneCare dashboards for caregivers and nurses.
Benete saved valuable time in documentation procedures, enabling caregivers to focus more on patients.
By creating prompt templates in watsonx.ai, Benete sourced variables, data and tasks from IBM Cloudant
Summary reports, which were previously generated and interpreted manually, are now instantly generated in less than 5 seconds
These prompts were then deployed in watsonx.ai to become endpoints where data is transformed into understandable insights and integrated into BeneCare.
there’s a 90% reduction in the time taken to understand client data
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.
The public Organization JSON-LD for Benete includes numberOfEmployees value 4; 4 maps to SMB under the enrichment thresholds.
Related
IBM Sample Feb 27, 2025 Center for BrainHealth The Center for BrainHealth needed to scale a longitudinal neuroscience study beyond manual, three-hour intake sessions and local high-touch processes without reducing participant engagement or scientific rigor. 65 countries AWS Cloud · Dialexa, an IBM Company 
Databricks Sample Oct 8, 2026 ModMed ModMed needed to protect sensitive patient data and maintain compliance while reducing administrative overhead, improving access to operational data, and creating AI-enabled products and agentic workflows for ambulatory… Databricks Data + AI Platform · Genie Agents · Genie Code IBM Sample Sep 28, 2026 OnticWorks.io OnticWorks.io needed its Elmer agentic platform to reason within the physical and operational context where work happens instead of relying on disconnected dashboards, emails, sensor feeds, and simulations that users… 12-month acceleration IBM Bob · IBM watsonx.ai · Red Hat OpenShift 