Key facts
| API surface | OpenAI-compatible /v1/chat/completions; keep your existing SDK |
| Grounding | Embeddings and RAG are live for operations, fares and crew knowledge 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 |
| 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 airline answers in approved internal content with RAG instead of model memory.
- Keep passenger or safety-sensitive 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 operational decision.
- Version manuals by fleet and revision so answers match the aircraft.
How it works, step by step
- Inventory the content to make searchable: operations manuals, fare rules, crew policies and irregular-operations playbooks.
- 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 dispatchers and training leads 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 RAG architecture builder →
Where airline teams start
Start with internal questions that already have a written answer. High-value first workloads include:
- Operations and IROPS playbooks: answer from irregular-operations procedures and station guidance.
- Fare rules and policy: retrieve fare conditions and ticketing policy for agent support.
- Crew and roster policy: answer scheduling, leave and duty questions from approved manuals.
- Maintenance and technical docs: surface task cards and service bulletins for engineer review.
Each use case augments staff with cited answers; none replaces duty manager judgment.
A private RAG architecture for airline knowledge
The stack is consistent across industries: ingest approved operations manuals, fare rules, crew policies and irregular-operations playbooks, 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.
Version control matters: index only current manuals and retire superseded revisions. Use JSON mode for structured outputs into operational tools, and keep a strict refusal path for questions outside approved documentation.
Access control, confidentiality and audit
Passenger and crew information, safety reports and negotiated fares are all sensitive, and aviation rules vary by jurisdiction. Keep identifiable passenger data out of the pilot corpus, use role-based retrieval filters for safety and commercial content, and log every query so safety and audit teams can review access.
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 data residency in AI for related deployment and control detail.
Rollout and human oversight
Pilot on public operations and policy documents before touching passenger or safety-sensitive content. Build a labelled question set with dispatchers and training leads, 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 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 operations, fares and crew knowledge 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 airlines 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 help with irregular operations?
Yes, as a retrieval aid during IROPS. It surfaces the current procedure and cites the source; dispatchers and duty managers still make and communicate every operational decision.
How do we handle multiple aircraft types?
Tag manuals by fleet type and revision, then filter retrieval by aircraft so answers always come from the correct documentation set.