Time for what matters
When AI lightens everyday life and makes expertise tangible.
Runtime for AI on FHIR®
Strong models alone are not enough. The technical environment determines whether AI is experienced as support.
AI in Digital Health – soon indispensable
The vision is clear: AI will tangibly improve everyday healthcare – more time for patients, less bureaucracy, better decisions. For this hope to become reality and for AI to truly support rather than burden, it needs a technical foundation that meets essential requirements:
Speed that matches cognitive processes — according to studies, the perceptual threshold for delays is approximately 70 ms. For AI to actually assist and support workflow, needed information must be directly available, without searching, without noticeable pause.
Reliable answers through clear standards — for stable AI support, data needs unambiguous and reproducible structures. Deterministic responses emerge when information is cleanly modeled and relationships are consistently mapped. This delivers stable, traceable results — a fundamental requirement for robust AI logic that builds trust and provides security.
Systems that can be flexibly extended — Digital Health evolves quickly, AI even faster. This requires architectures that can clearly delimited, low-risk, and predictable integrate new functions. This keeps technology future-proof and grows with requirements.
Security that can handle complexity — digital health data requires consistent protection. AI can only be used responsibly when access rights are clearly defined and systems are logically separated. This creates trust — the foundation for successful AI integration.
The game-changer: Runtime for AI with the complete DNA of
HealthRuntime is based on a simple idea: Digital health data should work where it originates – and strengthen people in everyday life. That's why we at atollee developed a Runtime for AI on FHIR® from the ground up.
Implemented with next-generation web technology and consistently edge-first – for secure processing and responsive AI starting at the point of care and in patient-facing applications.
One stack, one team: end-to-end TypeScript – from device to cloud. Tests against the FHIR® specification ensure reliable extensions – with AI as a partner in development and use.
Direct data processing without detours: shared FHIR® model and TypeScript type tree (StructureDefinition → TS) – consistent end-to-end.
Modularly extensible and standards-compliant: from prototype to production; 100 % FHIR®-compliant (R6-ready) and agent-friendly from the start.
Validation and terminologies where they matter: seamlessly integrated — in backend and frontend (direct feedback, offline capability, better usability) — compliant with the FHIR® specification and profiles.
HealthRuntime provides comprehensive support for modern data exchange in Digital Health – AI loves this:
FHIR® expertise is built-in — ready for what's next.
A foundation is future-proof when it enables change. HealthRuntime combines standards fidelity with modular architecture — flexible and adaptable.
Plugin-first architecture — open for existing resources and environments: on-device, at the edge, in clusters, in the cloud or serverless.
Digital health requires breadth and depth. HealthRuntime provides building blocks to implement requirements quickly and responsibly — agent-friendly in development and optimized for agentic AI. Teams gain time — and patients receive reliable, everyday support. Best-of-breed approach with collaborative mindset: systems work together and complement each other.
Safety & governance by design: zero-trust architecture, RBAC, policies, audit trails and observability — so automated recommendations remain traceable and accountability is clearly defined.
HealthRuntime as Clinical Data Repository (CDR)
| Hybrid DB (Native SQL + Inverted Indexes) | NoSQL-DB only | GraphDB only | |
|---|---|---|---|
| FHIR compliance | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(2/5) | 🔥🔥🔥🔥🔥(2/5) |
| ACID guarantees | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(2/5) | 🔥🔥🔥🔥🔥(3/5) |
| Performance (FHIR queries) | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(2/5) | 🔥🔥🔥🔥🔥(3/5) |
| Performance (Write) | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(3/5) |
| References & Hierarchies | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(2/5) | 🔥🔥🔥🔥🔥(5/5) |
| Reference lookups | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(2/5) | 🔥🔥🔥🔥🔥(3/5) |
| Full-text search | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(3/5) | 🔥🔥🔥🔥🔥(2/5) |
| Query flexibility | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(2/5) | 🔥🔥🔥🔥🔥(3/5) |
| Scalability (overall) | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(4/5) | 🔥🔥🔥🔥🔥(3/5) |
| Horizontal scaling | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(3/5) |
| Maintainability | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(3/5) | 🔥🔥🔥🔥🔥(3/5) |
| Cost (low) | 🔥🔥🔥🔥🔥(5/5) | 🔥🔥🔥🔥🔥(2/5) | 🔥🔥🔥🔥🔥(2/5) |
Best of both worlds: Transactional consistency + NoSQL performance 🔥🔥🔥🔥🔥(5/5) | Good for simple, large data collections, less suitable for FHIR® 🔥🔥🔥🔥🔥(3/5) | Good for graph analytics, less suitable for standard FHIR® 🔥🔥🔥🔥🔥(3/5) |
Regarding the database question, we recommend a hybrid DB approach combining relational DB & full-text search – from an Open Source stack (PostgreSQL + OpenSearch). This approach fits optimally with FHIR®, which is based on proven concepts from modern web technology that HealthRuntime can implement directly.
FHIR® + tool interfaces: interoperability meets orchestration.
FHIR® (Fast Healthcare Interoperability Resources) is the open, community-driven specification for interoperability and data exchange in healthcare — the "Fast" emphasizes rapid implementation and deployment. HealthRuntime implements it rigorously with the claim to be 100 % FHIR®-compliant. Interoperability succeeds through collaboration — through the willingness to exchange data between systems and use common standards.
Standardized tool interfaces enable clients and agents to access deterministic functions according to roles and permissions: structured, auditable calls with defined schemas — embedded in role- and permission-based access control.
Policy-compliant access via SMART on FHIR® (OAuth/scopes), RBAC and policies; technically integrated and enforced via the tool service. For Trust Communities and B2B transactions, UDAP (FAST Scalable Security) is available as a plugin.
Agents operate on released FHIR® context subsets with clear scopes — fully traceable. This creates transparency for teams and patients.
Agentic AI — easing everyday work, empowering people.
Agentic AI stands for context-aware automation: specialized agents support tasks in a rule- and context-guided way — transparent, safe, and in dialogue with users.
Own or external agents can be orchestrated via FHIR® contexts and standardized tools — for analysis, planning, interaction and integration; LLM-based, rule-driven or tool-assisted. HealthRuntime provides the technical foundation that makes this work. Result: teams gain time; patients receive clear, explainable support in everyday life.
Concrete examples: structured appointment preparation, medication checks with rationale, therapy-plan guidance, personalized reminders, symptom diaries — all based on approved data and fully auditable. Work relief that is tangible — so therapists and physicians have more time for what they chose to do: help people.
Ambient AI scribes reduce documentation burden and generate structured FHIR® data. Further developments: audio/visual feedback and hands-free (AR/XR).
Scaling Health AI – Edge-first, from the start
The way software is created is undergoing fundamental change: More focus on intent specification, orchestration, and verification — more efficient and goal-oriented.
At atollee, we translate this transformation into the healthcare context. Speed emerges through intent-driven, structured development, production-ready code from the first step, and reproducible, containerized deployments. Edge-first means for us: Health-AI runs where it's needed — locally at the Point of Care.
Our lean, high-performance HealthRuntime is specifically designed for efficient edge execution and is consistently deployed across all development and operational phases. This creates predictable behavior, auditability, and scalability — as system properties that are considered from the start. This is how we make modern AI development operational for the healthcare system. From proof of concept to scale — scalable when use cases prove their value.
Digital Health needs standards, speed, and modern architecture. If you're planning applications or AI workflows and want to experience the world's only FHIR-native runtime: Let's act.