Key facts
| API surface | OpenAI-compatible /v1/chat/completions; keep your existing SDK |
| Grounding | Embeddings and RAG are live for protocol, formulary and operations search |
| Models | 30+ models behind one API, from free tiers to frontier |
| Deployment | Plugsky cloud, your VPC, on-prem or air-gapped |
| Access control | Scoped API keys, rotation and usage analytics; enterprise SSO and RBAC options |
| Endpoint roadmap | Audio, images, moderation, batch and fine-tuning are coming soon |
| Pricing model | Flat monthly self-serve plans; no per-token billing on self-serve |
| Free tier | Free plan with plugsky-micro and plugsky-lite; 14-day full-access trial |
TL;DR
- Ground hospital answers in approved internal content with RAG instead of model memory.
- Keep patient-adjacent content inside VPC, on-prem or air-gapped deployments where policy requires it.
- Scope retrieval per team, client or site so permissions and confidentiality hold at query time.
- Keep a named human owner for every clinical decision.
- Index approved, de-identified content only.
How it works, step by step
- Inventory the content to make searchable: nursing protocols, formularies, scheduling policies and administrative procedures.
- Define a data boundary for the pilot that excludes restricted material until controls are proven.
- Choose a deployment target: cloud for public content, VPC, on-prem or air-gapped for restricted data.
- Build an evaluation set with nurse educators and pharmacists so answer quality is judged by domain experts.
- Ingest, chunk and embed approved documents, and require citations on every answer.
- Add refusal behavior for questions outside the indexed, approved content.
- Review logged interactions on a schedule and expand only after accuracy and access checks pass.
Original data
Try it yourself
Open the private LLM deployment estimator →
Where hospital teams start
Start with internal questions that already have a written answer. High-value first workloads include:
- Nursing protocols: answer procedure questions from approved clinical protocols.
- Formulary and medication policy: retrieve formulary rules and policy summaries.
- Scheduling and staffing policy: answer roster, leave and coverage questions.
- Administrative procedures: surface admissions, billing and compliance guidance.
Each use case augments staff with cited answers; none replaces clinical owner judgment.
A private RAG architecture for hospital knowledge
The stack is consistent across industries: ingest approved nursing protocols, formularies, scheduling policies and administrative procedures, chunk and embed with a multilingual embedding model, store vectors inside your environment, and call chat completions that answer only from retrieved context. Plugsky embeddings and chat completions are OpenAI-compatible, so teams already using OpenAI SDKs change the base URL and keep their code.
Unit, role and protocol version are the metadata that matter. Keep the index to approved de-identified content, use a reranker for long clinical documents, and require citations so reviewers can confirm the source.
Access control, confidentiality and audit
Patient-adjacent data, staffing records and clinical protocols require strict boundaries. Keep the corpus to approved, de-identified content, filter retrieval by role and unit, and retain logs for privacy and quality review. Clinical decisions always stay with qualified staff.
The technical controls are consistent: enforce permission-aware retrieval in your own service layer, scope API keys per application, team or tenant, rotate keys, and retain request and response logs on a defined schedule. Regulatory obligations vary by jurisdiction and sector, so map them with counsel rather than assuming one framework covers every deployment; Plugsky supplies the deployment and logging primitives you document.
See air-gapped AI for related deployment and control detail.
Rollout and human oversight
Pilot on published protocols and administrative policy before touching patient-adjacent content. Build a labelled question set with nurse educators and pharmacists, then measure retrieval hit rate, citation correctness and answer accuracy before and after every index or model change. Require citations on every answer, refuse out-of-scope questions, and name a human owner for every clinical decision.
Review logged interactions weekly at first, correct the index rather than the prompt when retrieval misses, and expand the corpus only when accuracy and access checks pass.
Honest comparison
| Capability | Plugsky | Public AI assistants | Building in-house |
|---|---|---|---|
| Data boundary | Cloud, VPC, on-prem or air-gapped | Vendor cloud only | You control fully |
| Grounding | Embeddings and RAG are live for protocol, formulary and operations search | Uncontrolled retrieval | You assemble and operate |
| Access control | Scoped keys, usage analytics, enterprise SSO and RBAC options | Account-level only | Custom identity work |
| Auditability | Request and response logging | Limited | You build logging |
| Pricing | Flat monthly self-serve plans; see live pricing | Per-seat or per-token | GPU plus operations cost |
| Time to pilot | Days | Hours, without residency control | Quarters |
Frequently asked questions
Can hospitals keep data private with Plugsky?
Yes. Choose the deployment boundary that matches the data: Plugsky cloud for public content, or your VPC, on-prem and air-gapped options for restricted material. Access is controlled with scoped API keys and usage analytics.
Do we need to fine-tune on our internal documents?
Not for a first release. Fine-tuning is coming soon and is better for style than facts. RAG keeps answers current, permission-aware and traceable to a source, which matters more for internal knowledge.
Which model should we use?
Start free with plugsky-micro and plugsky-lite to validate retrieval, then evaluate mid-tier and frontier models from the 30+ model catalogue on your own question set.
How do we stop wrong or unsupported answers?
Restrict the assistant to approved indexed content, require citations, refuse out-of-scope questions and keep a human decision-maker for every regulated or client-facing outcome.
How is pricing structured?
Self-serve plans are flat monthly with unlimited fair-use usage, and there are no per-token charges on self-serve plans. See the live pricing page for current plans and the free tier.
Can nurses use it at the bedside?
As a reference tool for approved protocols and policies, yes, with citations and human verification. It should not replace clinical assessment or judgment.
How do we handle formulary updates?
Version formulary documents by effective date, re-embed on change, and filter retrieval so only the current version is returned.