Patient support and intake
Answer patient questions and complete intake in less time. Clinicians and domain experts review the cases that need a person.
Bring reliable healthcare AI faster into production
Bring reliable healthcare AIfaster into production
For healthcare and life sciences teams: go live faster, spend less time on manual review, and keep costs in view as you scale. Merck Group reduced development cycles from weeks to days and runs 80+ use cases on Langfuse.
- 01
HIPAA-ready cloud region with a self-serve BAA: Sign the ClickHouse BAA, then send PHI only to the dedicated US region.
- 02
Self-host so patient data never leaves your network: Run Langfuse in your VPC or in an air-gapped environment.
- 03
Clinician or domain expert review in platform: Send traces and dataset items to annotation queues for clinicians or domain experts to review, correct, and pinpoint failure modes.
- 04
Quality gates and evidence for audits: Evaluate changes with datasets and experiments before going live, and keep traces and scores for review.
- 05
One platform for every AI team: Orchestrate one platform for tracing, evals, and cost tracking across teams. Govern centrally across the org.
Talk to a healthcare and life sciences expert at Langfuse
Used by 21 of the Fortune 50
90B+ observations/month
100,000+ engineers building on Langfuse
Used by 21 of the Fortune 50
90B+ observations/month
100,000+ engineers building on Langfuse
Run Langfuse where patient data is allowed to live
- 01
HIPAA-ready cloud region
A separate US region for healthcare and life sciences workloads. Sign the ClickHouse BAA before you send PHI. Docs →
- 02
Self-host or air-gap
Run Langfuse in your own network, including a deployment with no internet access. Patient data stays there. Docs →
- 03
Masking
Remove or replace PHI in inputs, outputs, and metadata before it is stored. Docs →
- 04
Access controls
SSO and role-based access scoped to organizations and projects. Docs →
- 05
Audit logs
Record prompt changes, membership changes, and other admin actions, with the user or API key that made the change. Docs →
Deployment mode
HIPAA-ready region in the US. BAA available.
Your app→OTel SDK→HIPAA region
- Region
- US, Oregon
- Location
- AWS us-west-2
- Agreement
- BAA available
- Plans
- Pro or higher
Prove it works before patients are impacted by your agents
Evaluate agents or datasets before release. Have clinicians and domain experts review the results and check that your AI judges agree with those labels.
Evaluate before release and in production
Offline evals, clinician or domain expert review, judge calibration, and production checks.
Offline evals with release gates
Run a dataset experiment on each change. Fail the release when a score drops below your threshold.
Docs →Clinician or domain expert review
Annotation queues are an in-app review flow. Clinicians or domain experts label traces and can save a corrected output before a release.
Docs →Calibrate AI judges
Score Analytics compares AI judge scores with clinician or domain expert labels. Agreement metrics include Cohen's Kappa, F1, Pearson, and Spearman.
Docs →Compliance and quality checks on production traces
Run compliance and quality checks with automated evaluators on production traces.
Code evaluatorsDecision model evaluatorsGovern AI systems
Control prompts, protect data, and manage access.
Prompt governance
Keep immutable prompt versions. Use labels for staging and production, and protect the production label.
Docs →Masking
Mask inputs, outputs, and metadata in the SDK before trace data leaves your application.
Docs →Access controls
Organizations and projects are the data boundary. Role-based access limits who can open a project.
Docs →Retention
Set a retention window per project. Export observations and scores to your own bucket when you need a longer archive.
Docs →Use cases
What healthcare and life sciences teams build on Langfuse.
Appointment booking
Book and change appointments with fewer failed or wrong bookings for staff to fix. Test representative cases before the agent goes live.
Medical information
Turn around inquiries from healthcare professionals in less time.
Clinical documentation
Draft clinical notes from visits and conversations, with less rework on the drafts clinicians review.
Payer and claims workflows
Catch failing claim steps early, before they become manual rework, and keep a trace for audit.
Voice agents
Find where a voice conversation lost context and correct it. Evolve cut Rest's memory misses in half.
Evolve: Rest sleep coach
Internal platform teams
Share traces, prompts, evaluations, and cost across teams, so the same platform works company-wide.
Merck Group: 80+ use cases on Langfuse
Learn how to ship reliable agents in healthcare and life sciences
Start with datasets and release gates. Then read how Merck Group and Evolve use Langfuse.
Building deployment gates for LLMs
Evaluate model and prompt changes against datasets before release.
Academy: designing datasets
Design ground-truth datasets with clear inputs, expected outputs, and a review rubric.
Merck Group customer story
How Merck Group serves 80+ AI teams on self-hosted Langfuse.
Evolve customer story
How Evolve traces and evaluates Rest, a voice-and-text sleep coach.
FAQ
Create a fresh Langfuse Cloud account in the HIPAA-ready region. The region runs in Oregon (AWS us-west-2) at hipaa.cloud.langfuse.com. Subscribe to the Pro plan or higher. Complete and sign the ClickHouse Business Associate Agreement via Ironclad before you process PHI. That form is the ClickHouse BAA for Langfuse HIPAA Cloud. It asks for your Langfuse organization ID. Where to find the organization ID. Send HIPAA-regulated data only to that region. It is separate from the EU, US, and Japan regions. In a self-hosted deployment, Langfuse does not receive or process your data, so no BAA with Langfuse is involved. You implement the HIPAA safeguards in your own environment. HIPAA docs.
Configure SDK masking to remove or replace sensitive inputs, outputs, and metadata before trace data leaves your application. You can also apply masking in an OpenTelemetry Collector inside your infrastructure. Self-hosted Enterprise can mask again during ingestion. SDK masking, server-side masking.
Eligible plans are the Pro plan or higher, in the HIPAA-ready region. Customers on those plans can sign a BAA before they process PHI. HIPAA docs, Cloud pricing.
Langfuse's observability integrations collect and export traces in the background while your application continues to call its model provider or gateway. You do not need to route model requests through Langfuse to use observability. If you also use prompt management, SDK caching and fallback prompts help keep your application resilient to connectivity issues. Background export, prompt availability.
Yes, on a self-hosted deployment. LLM-as-a-judge calls the model in an LLM connection. Point that connection at a model endpoint inside your network, and allow the host in the self-hosted LLM connection settings. On Langfuse Cloud, the connection base URL has to be a public HTTPS endpoint. LLM connections, self-hosted LLM API.
Working on AI in healthcare and life sciences?
Talk through the HIPAA-ready region, self-hosting, and how Merck Group and Evolve use Langfuse.
No credit card required, free tier available, self-hosting option
Was this page helpful?