If you’re building in care, we can provide the code

Construe applies LLM-powered RAG technology specifically designed for extracting key medical concepts from unstructured data with core medical terminologies.

Inputs: Almost any raw clinical text.

Outputs: Fully structured JSON or a hybrid output that preserves original text snippets alongside structured codes. All processing is HIPAA-compliant and performed on secure infrastructure.

Supported vocabularies: CPT, ICD-10-CM, ICD-10-PCS, SNOMED, LOINC, RxNorm, HPO, and custom.

Data processing: Domain-trained language models to understand clinical context, disambiguate terms, and handle shorthand, typos, and varying documentation styles. Every code includes confidence scores and highlighted source text for auditability.

Take the messy, unstructured reality of healthcare language and turn it into clean, standards-compliant FHIR® resources you can use confidently in your systems.

Inputs: Almost any raw clinical text.

Outputs: Properly structured FHIR resources. The API returns a JSON bundle ready to store in your EHR, feed into analytics pipelines, or trigger alerts in clinical decision support systems. All processing is HIPAA-compliant and performed on secure infrastructure.

Data processing: Both general clinical language and specialty-specific vocabularies. It recognizes not only terms but also context — negations (“no history of diabetes”), temporality (“started 2 weeks ago”), and relationships between entities.

Process multiple documents in parallel with efficient batch APIs.

From diagnosis codes to lab tests, every major medical terminology is searchable with both keyword and semantic search using Codify. Whether a patient says “sugar disease” or a doctor writes “diabetes mellitus type II”, the API finds the right codes.

Supported terminologies: ICD-10, SNOMED, CPT, RxNorm, and LOINC.

Code validation: Validate codes against current terminology versions.

Cross-system discovery: Search once and see diagnosis codes, related medications, lab tests, and procedures — all connected through a single query. Code Search automatically maps between ICD-10, SNOMED, and other terminologies. Look up any medical code to see its full description, extended definition, and system context.

Hierarchy navigation: Browse parent/child relationships and find related codes.

Getting from point A to point B in healthcare AI development is never a straight line. With Workflows, all you have to do is describe what you want to happen, and the API will create an executable plan that chains multiple steps together.

Create workflows for lab alerts, prior authorizations, care gap outreach, patient onboarding, and more.

Visual pipeline builder: Drag-and-drop interface for building complex clinical workflows.

Error handling: Built-in retry logic, fallbacks, and error notifications.

Audit logging: Complete audit trail of every workflow execution for compliance.

Your AI-native healthcare assistant. A single API that coordinates multiple specialized models to handle complex clinical and operational requests.

Inputs: Send any healthcare-related question or task prompt — from “summarize this patient’s chart” to “draft a prior authorization letter” — to the Agent API.

Outputs: Returns a ready-to-use result — whether that’s structured data, a written document, or a decision-support recommendation — optimized for direct use in workflows or EHRs.

Data processing: Automatically routes the request through the right combination of domain-specific AI tools, including Lang2FHIR, Construe, and custom reasoning modules. It pulls in relevant patient data, clinical guidelines, and terminology standards to ensure the response is accurate, compliant, and medically grounded.

HIPAA-compliant: All processing is HIPAA-compliant with BAA available.

Transform FHIR patient bundles into human-readable clinical summaries. Generate discharge documentation, referral letters, lab interpretations, and International Patient Summaries.

Template-driven narratives: Create reusable templates from example summaries, then populate them with new patient data. Placeholders are automatically extracted and mapped to FHIR resources.

IPS Document Generator: Generate a structured International Patient Summary from a FHIR bundle. The IPS follows ISO 27269, organizing clinical data into standardized sections for cross-border interoperability.

Output modes: Flatten (converts FHIR data into searchable plain text), Narrative (generates clinical narrative documents), and IPS (ISO 27269 International Patient Summary).

Describe your patient criteria using plain language and Cohort Builder queries your FHIR data to define patient populations instantly. As you refine criteria, you’ll see cohort counts update instantly so you can find the right population, every time.

Inputs: Define cohorts using plain English, e.g.; “Patients with diabetes over 65.” Express inclusion and exclusion criteria naturally.

Outputs: Instant cohort sizing with FHIR search decomposition. Preview the sample patient records that will be uploaded, and toggle to the live API to save them to your FHIR provider.

Exports: CSV, FHIR Bundle, or integrate with other systems.