Key facts
| Deployment | Cloud, VPC, on-prem and air-gapped with no outbound connectivity |
| Access control | Scoped API keys with rotation; enterprise SSO and RBAC options |
| Auditability | Request, model and response logging for incident review |
| Data grounding | Embeddings and RAG are live for runbooks and asset documentation |
| Resilience | Multi-model fallback and status visibility for degradation planning |
| Models | 30+ models behind one API for operations and knowledge workloads |
| Pricing model | Flat monthly self-serve plans; no per-token billing on self-serve |
| Endpoint roadmap | Images, audio, moderation, batch and fine-tuning are coming soon |
TL;DR
- Treat AI as an operational dependency: plan its failure, not just its access.
- Keep OT-adjacent and sensitive workloads on-prem or air-gapped.
- Separate keys by system and privilege level, and review them often.
- Require human authority over any action that affects physical operations.
- Log interactions and rehearse incidents before go-live.
How it works, step by step
- Map every AI workflow to the systems it reads or influences, marking OT-adjacent ones.
- Decide the boundary per workflow: cloud for public content, on-prem or air-gapped for operations.
- Define the degraded mode: what happens when the model is slow, unavailable or wrong.
- Scope keys by system and privilege, with rotation and a central inventory.
- Ground operational answers in version-controlled runbooks and require citations.
- Log request IDs, model versions, sources, outputs and human decisions.
- Run failover and incident drills, including disabling a workflow quickly.
Try it yourself
Open the AI API key security checklist →
OT and IT boundaries
Most critical infrastructure has a deliberate gap between operational technology and corporate IT. AI workflows must respect it. Review and knowledge tools belong on the IT side; anything that reads operational data or influences control decisions belongs inside the boundary, usually on-prem or air-gapped.
Document each data path from source system to model and back. If a workflow crosses the boundary, it needs an explicit, reviewed justification and a reversible design.
Availability, failover and safe degradation
AI becomes a dependency the moment operators rely on it. Define what happens when it fails: a cached answer, a manual runbook, or a clearly displayed degraded status. Use a fallback model per task class, bound retries and timeouts, and make sure a slow model cannot stall an operational process.
Test the failover path in drills, not in production. The status page gives visibility into platform health, but your own degraded-mode behavior is your responsibility.
Privileged access and keys
Issue keys per system and privilege level, store them in a secrets manager, and never let a read-only knowledge assistant share credentials with a tool that can change configuration. Rotate on schedule and after role changes. Enterprise SSO and RBAC options keep console permissions tied to your identity lifecycle.
Log tool calls with their arguments, because that is the record of what the system asked for and what it received.
Incident response and drills
Write the playbook before launch: who can disable a workflow, how fast that can happen, and how operations continue meanwhile. Rehearse three scenarios - wrong answer, unavailable model, suspected data exposure - and record how long each response takes. After every drill, fix the slowest step first. See disaster recovery and failover for recovery patterns.
Honest comparison
| Control area | Plugsky capability | Common gap | Owner |
|---|---|---|---|
| OT boundary | On-prem and air-gapped deployment with no outbound calls | Operational data in shared tools | OT security |
| Resilience | Multi-model fallback and status visibility | No defined degraded mode | Operations |
| Privileged access | Scoped keys per system and privilege level | Shared credentials across roles | Security engineering |
| Audit trail | Request, model and tool-call logging | No reconstruction path | Incident response |
| Runbook grounding | RAG over version-controlled procedures | Answers from stale documents | Operations engineering |
| Human authority | Retrieval and summarization only, with review gates | Automated operational actions | Control room lead |
Frequently asked questions
Can AI touch operational technology directly?
No. Keep it in a retrieval and advisory role. Any action affecting physical operations goes through a human decision and your existing control systems.
What does safe degradation look like?
A defined fallback: cached guidance, manual runbooks or a clearly marked degraded state. Rehearse it and measure how long the switch takes.
How do we isolate sensitive operational data?
Use on-prem or air-gapped deployment with no outbound connectivity, keep indexes inside the boundary, and document each data path for review.
What should we log?
Request IDs, model and version, retrieved sources, tool calls with arguments, outputs and human decisions. That record supports incident investigations and audits.
Is multimodal analysis available for inspections?
Image and audio endpoints are coming soon. Today, send extracted text from inspections or logs through the live chat and embedding APIs.
How do we manage keys across many systems?
One key per system and privilege level, central storage, scheduled rotation and quarterly inventory reviews. Revoke immediately when roles or vendors change.
Where should a pilot start?
Use public standards and internal runbooks on the free plan, prove citation accuracy and logging, then extend to operational data inside the boundary.