We're delighted to share that lang2FHIR now supports extracting multiple FHIR resources from a single request text. Upload an entire medical note and watch lang2FHIR generate derived FHIR resources for you either standalone or as part of a FHIR server integrated flow using tools!

fhir2summary now supports International Patient Summary mode!

When you use fhir2summary with IPS mode it will take your FHIR bundle and generate International Patient Summary narratives per ISO 27269 and HL7 FHIR IPS IG standards. Auto-creates sections for allergies, medications, problems, immunizations, procedures, and vital signs. No template is required, you just set mode to ips. Requires Bundle with exactly one Patient resource with identifiers.

Use cases: context engineering, care transitions, referrals, cross-border exchange, standardized summaries.

We've released a Claude Code plugin that lets you use Claude as a forward deployed agent for building healthcare data workflows.

Describe what you need in plain language (e.g. FHIR mapping pipelines, data transformations, EHR integrations) and Claude orchestrates Phenoml APIs to build it for you. The plugin connects Claude directly to our workflows and FHIR Provider APIs!

Use it to:

• Prototype FHIR mapping pipelines by describing the transformation you need
• Build and iterate on healthcare workflows conversationally
• Get started with phenoml APIs without leaving your terminal

Check out the tutorial video to see it in action!

We're excited to announce the beta release of fhir2summary - a new feature of lang2FHIR that enables you to compress and summarize FHIR resources!

At release fhir2summary supports two modes: narrative and flatten. Flatten mode converts FHIR resources to a stringified form inspired by the work of Sam Schiffman. Narrative mode enables you to create custom templates for summaries you want to generate from FHIR resources. You can create summary templates for use cases ranging from context engineering, FHIR data compression, to chart summarization. Provide fhir2summary an example summary and representative resources and our AI will generate a reusable template for you to use on subsequent resources.

Coming soon:

• auto mode for narrative (e.g. generate summary templates automatically)
• enhanced flatten mode (improved semantic clarity for flattened FHIR resources)

We're excited to announce the beta release of workflows - orchestrate healthcare data operations using natural language!

Workflows uses lang2FHIR to translate your natural language instructions into structured FHIR operations and generates a DAG of steps – FHIR searches, resource creation, and decision nodes. Pass in unstructured data like clinical notes or legacy system outputs, and workflows handles extraction, transformation, and orchestration across your FHIR systems.

You can execute workflows across multiple FHIR providers (Epic, Cerner, Athena Health, Elation, Medplum, Canvas Medical, Google Healthcare API, HAPI) or a single one by specifying the fhir_provider_id in your workflow requests! Control whether to use deterministic templates (default) or dynamic generation. One seamless API for healthcare data orchestration.

Coming soon:

• Workflow composability (reference other workflows as steps)
• Enhanced decision node logic
• Workflow instruction templates for common use cases
• LLM assisted workflow authoring
• Self-healing workflows

We’re delighted to share the release of a much improved solution for customers to add their own FHIR integrations for tools and agents built on phenoml to utilize.

We currently support customers registering FHIR servers for AI-native integration on EPIC, Cerner, Elation, Athena Health, Medplum, Canvas Medical, Google Healthcare API, and HAPI! Auth is currently backend oauth and tools and agents can utilize backend SMART on FHIR flow.

You can seamlessly swap in and out the different FHIR providers you’d like to connect your tools and agents to by changing the fhir provider ID in your tools and agents API requests! One seamless API, endless healthcare AI opportunities.

Coming soon:

• Practice Fusion
• Salesforce Health Cloud
• Healthie

We've updated our pricing to make it even easier to get started building with phenoml.

• We have a new Hobby tier so you can start building for free!
• PhenoTools and PhenoAgent are now available on Hobby & Experiment tier 🙌
• We've updated our pricing model for predictable cost tracking- making it easier for you to track and monitor your costs as you scale. No estimating API usage, no complicated tokens, just pick the plan that works best for your organization.

We're thrilled to announce the release of our phenoml Typescript and Java SDKs 🎉

Enjoy a more pleasant and productive experience working with phenoml APIs!

Check it OUT!

• typescript
• java

🔌 MCP Server support

It’s here! You can now add MCP servers as tools to PhenoAgents!

Use cases enabled include using phenoml APIs via MCP, building agents that can search for clinical trials, get resources from the internet (e.g. clinical guidelines, etc.) to inform clinical workflows, or enable a patient or caregiver to book an appointment and then get directions.

😎 Coming soon!

• Oauth support for MCP
• Built-in MCP server support for popular use cases (e.g. clinical trials gov, pubmed, google maps, etc.)

We're thrilled to announce the release of our PhenoML Python SDK 🎉

Enjoy a more pleasant and productive experience working with PhenoML APIs!

Check it OUT!

💡 Coming soon!

• Java SDK (under development)
• Go SDK
• Typescript SDK