Normalized claim
Users comfortable sharing sensitive information: 79% increase
“79% of users reported feeling comfortable sharing sensitive information.”
MyLÚA Health builds an agentic perinatal care platform with watsonx Orchestrate and watsonx.ai
Use case typePatient engagementUpdated Feb 11, 2026
MyLÚA Health built a secure agentic AI platform for pregnancy and postpartum support that gives birthing parents immediate, privacy-preserving guidance between clinical visits. The platform uses curated evidence content across pregnancy, postpartum care, nursing, mental health and nutrition, with a FastAPI backend on IBM Cloud Code Engine and orchestration through IBM watsonx Orchestrate and watsonx.ai.
- Organization
- MyLÚA Health
- Industry
- Healthcare
- Location
- United States
- Published
- February 2026
Reported outcomes
+79%
users comfortable sharing sensitive informationAdoption & scale
Strategic outcomes
Other strategic outcomeDelivered timely prenatal and postpartum support outside clinical visitsBetter decisions & insightReduced manual documentation for doulas and care teamsOther strategic outcomeProvided anonymized trend data for employers and health plansCustomer experience & trustMaintained privacy-preserving support with sensitive data controls
Why do we believe this?Outcome claims, sources, and evidence checks
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- MyLÚA Health
- Provider
- IBM
- Maturity
- Unknown
- Linked source
- IBM
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 2 of 2
- 1Patient engagement
- 2Healthcare workflow automation
- Traditional healthcare workflows detect pregnancy and postpartum risks too late.
- MyLÚA Health needed always-available support that protects privacy and reduces manual documentation for care teams.
- Built an agentic chat platform where birthing parents choose which agent to engage.
- Used retrieval-augmented generation on curated evidence-based content across five domains.
- Ran a FastAPI backend on IBM Cloud Code Engine for scalable serverless execution.
- Used IBM watsonx Orchestrate for agent execution and tool invocation, and watsonx.ai for grounded responses.
- Added web search, reminders, check-ins and multilingual support, with separate machine-learning risk modeling for early indicators.
- Users can get timely guidance outside normal care hours.
- Doulas and care teams receive structured summaries that reduce manual documentation.
- Employers and health plans receive anonymized trend data.
- The platform improved trust and comfort in sharing sensitive information.
Architecture
A FastAPI service runs on IBM Cloud Code Engine. User-facing clients span mobile and desktop. Data persistence uses PostgreSQL and Redis with role-based consent and tokenization. Sensitive data is never sent to LLMs. AI workflows are executed with IBM watsonx Orchestrate for agent execution and tool invocation, and watsonx.ai for grounded generation. The system uses retrieval-augmented generation over curated evidence content and supports background jobs, reminders, check-ins and multilingual interactions. Risk modeling is handled separately with machine-learning models for early indicators such as depression.
Sources & evidence1
Evidence: Low35/100Evidence strength
- Customer explicitly identified
- Quantified outcome available
- Technical implementation details available
Type: Blog PostPublished: Feb 11, 2026Publisher: IBMEvidence: VendorConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.