ETERNO: Agentic AI for outpatient care summary and medical record processing on AWS

German start-up ETERNO is building an AI assistant for outpatient care across Europe. Its agent Leni works across 50 medical fields to summarize medical records, transcribe and summarize doctor-patient conversations with consent, store summaries in patient records, and support doctors with better decision-making and financial insights.

Organization
ETERNO
Industry
Healthcare
Location
Germany
Published
July 2026

Reported outcomes

30 seconds

medical record summarization timeTime & speed

−90%medical record processing time3 clinicsclinic deployment count

Strategic outcomes

Employee experienceEnabled more flexible doctor workSpeed & agilityRapidly deployed to users in weeksRisk & complianceMet healthcare privacy and compliance requirements

Primary read

Use case focus

Showing 2 of 2

  • 1Clinical documentation
  • 2AI agents
  • Physicians have limited time to process diverse incoming health data and make decisions quickly.
  • Small clinics often rely on traditional on-premise IT, and digital healthcare workflows are hard to modernize while preserving security and privacy.
  • ETERNO built Leni, an AI agent that summarizes medical records in about 30 seconds and provides streamlined information to doctors.
  • The system transcribes and summarizes doctor-patient conversations with consent and stores the output in patient records.
  • ETERNO built clinics in Germany to test the agent in modern clinical workflows and uses AWS as the infrastructure stack for booking tools, AI agents, and automated billing.
Technologies
  • Doctors can work remotely and more flexibly.
  • The company is testing the solution in three clinics and plans a wider release.
  • The solution helps doctors gain a holistic understanding of the patient more quickly.
Sources & evidence1
Groundedness: 5/5Type: Customer StoryPublished: Jul 8, 2026Publisher: AWSEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?