Key facts
| API surface | OpenAI-compatible /v1/chat/completions; keep your existing SDK |
| Grounding | Embeddings and RAG are live for procedures, maintenance and incident knowledge |
| 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 |
| Auditability | Request and response logging with usage analytics |
| 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 critical infrastructure answers in approved internal content with RAG instead of model memory.
- Keep network or operational 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 safety or operational decision.
- Keep vectors and logs inside the site or corporate network.
How it works, step by step
- Inventory the content to make searchable: operating procedures, maintenance manuals, incident runbooks and vendor documentation.
- 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 operations and maintenance engineers 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 sovereign AI readiness score →
Where critical infrastructure teams start
Start with internal questions that already have a written answer. High-value first workloads include:
- Procedures and permits: answer from operating procedures, permits and isolation standards.
- Maintenance and asset docs: retrieve manuals, work orders and asset histories.
- Incident runbooks: surface response procedures and escalation paths under pressure.
- Vendor and inspection docs: answer from vendor manuals, inspection reports and filings.
Each use case augments staff with cited answers; none replaces authorized operator judgment.
A private RAG architecture for critical infrastructure knowledge
The stack is consistent across industries: ingest approved operating procedures, maintenance manuals, incident runbooks and vendor documentation, 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.
Keep the index close to operations: on-prem or air-gapped deployment, metadata filters for site and asset, and a reranker for long procedure documents. Answers should always show the procedure and revision they came from.
Access control, confidentiality and audit
Operational procedures, network details and incident records are restricted. Keep them in an isolated environment, filter retrieval by site and role, and treat model output as advisory: nothing generated should drive switching, maintenance or safety decisions without a qualified operator's approval.
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 critical infrastructure deployment options for related deployment and control detail.
Rollout and human oversight
Pilot on public standards and training material before touching network or operational content. Build a labelled question set with operations and maintenance engineers, 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 safety or operational 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 procedures, maintenance and incident knowledge | 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 critical infrastructure operators 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 it run fully offline?
Yes. Air-gapped deployment keeps models, vectors and logs on your network with no external connectivity, which suits control rooms and regulated sites.
Who approves answers that affect operations?
A qualified operator or engineer must approve any action taken from a generated answer. The assistant provides cited drafts; it does not authorize switching, maintenance or safety decisions.