Feature × Audience

How does healthcare run air-gapped AI on Plugsky?

Healthcare runs Plugsky air-gapped by deploying open-weight models and the runtime inside the hospital or health-system network, so PHI never traverses an external path. The internal endpoint stays OpenAI-compatible, keeping clinical applications portable, while controlled update intake, SSO/SCIM identity and SIEM-exportable audit events make every access reviewable. Clinical decisions remain with licensed staff.

Key facts

Data boundaryPHI stays inside the perimeter; no internet path for inference or logs
DeploymentOn-prem and air-gapped tiers alongside cloud and VPC options
ModelsOpen-weight models suitable for offline operation in the catalogue
API contractOpenAI-compatible endpoints; application code unchanged across tiers
Safe scopeSummarisation, drafting, coding support and search; clinicians decide
UpdatesControlled intake with verification on your cadence
AuditAccess, key and inference events exportable to internal SIEM
StatusLive platform; enterprise deployment terms per engagement

TL;DR

  • PHI stays inside the health system network — no egress at all.
  • Keep clinical judgement with clinicians; agents summarise and draft.
  • Treat model updates as validated releases with staging and rollback.
  • Log every access so investigations have evidence.
  • Start with documentation workloads, not diagnosis.

How it works, step by step

  1. Confirm which workloads need a full air gap versus a VPC or on-prem deployment with controlled egress.
  2. Choose administrative and documentation use cases first: discharge summaries, referral letters, coding support and policy search.
  3. Size GPU capacity for clinical concurrency, including peak and failure headroom.
  4. Deploy the runtime and verified open-weight models inside the network, with an inventory of versions and provenance.
  5. Integrate SSO/SCIM for clinical and administrative staff, and scoped keys for services.
  6. Keep record-system tools read-only, routing drafts into clinician review queues rather than writing directly.
  7. Stream access, key and inference events to internal SIEM, and validate output quality with clinical reviewers before scaling.
1Confirm whichworkloads need afull air gap versus2Chooseadministrative anddocumentation use3Size GPU capacityfor clinicalconcurrency,4Deploy the runtimeand verifiedopen-weight models5Integrate SSO/SCIMfor clinical andadministrative6Keep record-systemtools read-only,routing drafts into

Try it yourself

Open the AI data residency checklist →

Why healthcare considers air-gapped AI

Health systems hold data that cannot be casually moved: patient records, imaging metadata, clinical notes and billing detail. Even where a compliant cloud deployment exists, some organisations — or some workloads — require that processing never leaves the perimeter. Air-gapped Plugsky satisfies that requirement by running open-weight models and the runtime inside the network with no internet path.

The API stays OpenAI-compatible, so clinical applications, prompt libraries and evaluation harnesses built in a pilot environment transfer to the isolated estate unchanged. That continuity is what keeps a two-year compliance programme from becoming a two-year engineering project.

Safe workload design

Start where errors are cheap to catch and clinicians already review. Documentation summarisation, referral drafting, coding suggestions with citations, patient-message triage and internal policy search all fit. Nothing the agent produces reaches the record or the patient without human review, and every draft records model version, prompt version and reviewer.

  • No autonomy: diagnosis, prescribing and triage decisions stay with licensed staff.
  • Minimise: even inside the perimeter, strip identifiers the task does not need.
  • Review metrics: track acceptance, edit distance and override reasons to prove the workflow helps.

Updates, audit and investigation readiness

Air-gapped estates need disciplined refreshes. Treat model and runtime updates as validated releases: checksums, scanning, staging on a mirror of production, evaluation against clinical test cases, then promotion with rollback ready. A version manifest prevents the silent drift that makes quality regressions impossible to explain.

Audit is the other half of safety. Export access, key and inference events to internal SIEM so any incident can be reconstructed: who accessed what, which model produced which draft, and who reviewed it. Combined with short retention for sensitive material, this gives privacy officers a defensible position without external dependencies.

Honest comparison

Healthcare requirementPlugsky air-gappedCloud AI serviceDIY open-source stack
PHI boundaryNever leaves the perimeterRequires DPA and controlsDepends on your build
Clinical safeguardHuman review enforced in your applicationVariesYou implement
Update validationControlled, staged, rollback-readyProvider-scheduledYour process
AuditEvents export to internal SIEMVendor logsYour pipelines
API compatibilityOpenAI-compatible offlineVendor APIYou define it
EffortDeployment and pipelineLowestHighest

Frequently asked questions

Does any PHI leave the hospital?

No. In an air-gapped deployment, inference, embeddings and logs remain inside the perimeter with no external network path. Minimisation still applies as defence in depth.

Can agents write to the medical record?

They should not write directly. Keep record-system tools read-only and route drafts into clinician review queues, with the final entry made by a person.

How are model updates validated?

As staged releases: checksums, scanning, validation on a production mirror using clinical test cases, then promotion with a tested rollback path.

What should we log?

Access events, key lifecycle changes and inference metadata such as model and prompt version plus timestamps. That lets privacy officers reconstruct any incident from evidence.

Which workload should come first?

Documentation and coordination: discharge summaries, referral letters, coding support and policy search. They save time without touching clinical judgement.

How do we measure clinical value?

Track draft acceptance, edit distance, override reasons and time saved per case. Review a clinical sample monthly and before expanding scope.

How do we start?

Prototype on de-identified data, then move the same code path into the isolated estate. Enterprise engagements cover deployment review and support terms.