Risk Management
MyLÚA Health needed an enterprise-ready way to deliver culturally attuned maternal support between appointments while protecting sensitive health information and identifying risk earlier in underserved populations.
Reported impact
MyLÚA validated early clinical and engagement results, improved trust with users and created a scalable platform for maternal support that can reduce risk and administrative burden.
MyLÚA Health partnered with IBM to build a multi-agent maternal-wellness platform that combines support, personalization and risk detection. IBM watsonx.ai provides the governed multilingual AI environment used to personalize responses and apply responsible AI controls, while IBM watsonx Orchestrate coordinates specialized agents across emotional, physical and social support domains. The platform runs on IBM Cloud with IBM Cloud Code Engine using FastAPI, Postgres and Redis so it can scale securely for regulated workloads. Users interact with the LÚA experience through mobile channels, and the agents translate those requests into check-ins, reminders, education and local resource activation. The same platform also supports structured summaries for doulas and care coordinators and early identification of postpartum-depression risk, all while keeping personally identifiable and protected health information away from large language models.
User interactions flow into the IBM Cloud-hosted LÚA platform, where watsonx.ai interprets context, watsonx Orchestrate coordinates specialized agents and application services return guidance, reminders, summaries and resource actions while keeping sensitive data outside LLM prompts.
IBM watsonx Orchestrate coordinates specialized agents across emotional, physical and social domains.
MyLÚA partnered with IBM to design, test and deploy its multi-agent maternal-wellness platform underpinned by IBM watsonx.ai®, IBM watsonx Orchestrate®, IBM Cloud® and IBM Cloud Code Engine.
The platform’s privacy-preserving design further supports healthcare-grade governance and scalability because personally identifiable information and protected health information are not sent to large language models.
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
IBM Sample Dec 10, 2025 Global Pharmaceutical Manufacturer A global pharmaceutical manufacturer needed faster, more standardized supply-chain risk analysis because manual classification, fragmented documentation, and limited visibility into alternate suppliers and materials… >1500 risk events assessed, triaged and escalated to executives as needed AWS cloud services · IBM watsonx · IBM watsonx Orchestrate IBM Sample Apr 16, 2024 Innocens BV Innocens BV needed a faster, more reliable way to detect signs of late-onset sepsis in vulnerable newborns because NICU teams were relying on manual interpretation of many data sources and could miss critical changes… approximately one in five preterm neonates born under 3.3 pounds (1,500 grams) experience late-onset sepsis IBM Cloud Pak for Data · IBM Watson Machine Learning · IBM Watson Studio 
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 