Hospital Network Ties Infrastructure Health to Care Continuity With Ollandi
Summary
A hospital network operating several hospitals and clinics on shared infrastructure deployed Ollandi to measure infrastructure health by its effect on care. Clinical leaders now see which departments and systems are affected by an incident, and IT prioritises repairs by patient impact.
Before Ollandi
- IT measured health in technical terms such as CPU, link utilisation and disk latency.
- Clinical leaders could not quickly determine which wards or systems an incident affected.
- Shared workstations and shift changes made identity activity difficult to assess.
After Ollandi
- Each infrastructure component is mapped to the clinical services and sites that depend on it.
- Incidents are reported by hospital, department and clinical system, with available alternatives.
- Repairs are prioritised by effect on patients rather than order of alerts.
- Access that does not match normal shift patterns, location or role is raised for review with its event history.
Deployment
- Product: Ollandi, reasoning over infrastructure telemetry, identity events and network state. It does not read clinical records.
- Operating control: Observe & Notify.
- Any action that could affect clinical work remains a decision for care leadership.
By the numbers
Measured across Glemad's production deployments and published in the ADT research paper:
- Mean time to detect: 0.8 minutes, against an industry average of 287 minutes.
- Intent classification accuracy: 97% in separating legitimate automation from attacker behaviour.
These figures come from environments with mature telemetry and defined policy baselines. Results depend on the quality of the telemetry available.
