Run it inside your perimeter. With AI, or without.
Camlin Connect deploys from shared Sydney cloud to fully air-gapped infrastructure. A validated No-AI runtime mode runs services with zero model calls, identity plugs into the OIDC provider you already operate, and the speech stack is Australian-built with documented lineage. Built by an Australian vendor with production heritage inside a high-security defence-sector network.
Deploy without AI today. Enable it per step type as Australian frameworks land.
Australia’s AI governance is moving quickly — the Office of AI stood up in July 2026, with mandatory AI standards expected to follow. Camlin Connect decouples the decision: launch deterministic voice and chat services now, then switch on AI capabilities step type by step type, on your timetable, as your agency’s policy settles. No re-platforming, no rebuild.
Zero model calls. Enforced, not promised.
A closed list of AI-bound steps
Every step type in a service Blueprint is classified. Only three step types can ever touch a model — AI intent, AI sentiment, AI generate. Everything else is deterministic: menus, forms, data capture, routing, integrations.
Rejected at save time
Mark a Blueprint "No AI in runtime" and the platform refuses to save any version containing an AI-bound step. Non-compliant designs cannot reach production in the first place.
Hard-stopped at runtime
Defence in depth: even if a non-compliant flow somehow reached the runtime, execution halts before any model call is made. Flagged services run with zero AI provider keys configured.
Design-time AI stays separable: teams can use AI to draft and review Blueprints while the running service remains fully deterministic.
From shared Sydney cloud to air-gapped
Shared cloud
ShippedMulti-tenant SaaS in AWS ap-southeast-2 (Sydney). Fastest path to a working service; data stays in-region.
Dedicated
ShippedSingle-tenant infrastructure, isolated compute and storage, operated by Nuamedia. For teams that need separation without running it themselves.
Customer cloud
ShippedThe platform runs inside your AWS or cloud account, under your controls, your network boundaries, and your monitoring.
Offline / air-gapped
ShippedRuns entirely inside your perimeter. Licences are Ed25519-signed files verified locally — no activation call, no telemetry required to operate.
Your identity provider. Your keys. Your controls.
Standards-based OIDC
ShippedToken validation is standard OIDC/JWT via JWKS. Keycloak, Azure AD, Okta, Auth0, Cognito and other compliant issuers plug in — including identity providers running inside an air-gapped network.
Keycloak claim preset
ConfigurablePluggable claim mappers ship with Keycloak and standard-OIDC presets, so self-hosted identity maps onto platform roles without custom code.
Roles stay in the platform
ShippedOwner, admin, editor and viewer roles are managed in-platform and are independent of the identity provider — swapping IdPs never rewires who can do what.
Bring your own AI keys
ShippedWhere AI is enabled, tenant-scoped keys for OpenAI, Azure, Google and Deepgram keep the commercial and data relationship between you and your chosen provider.
The voice layer is sovereign too
Camlin Speech is an Australian-built speech stack — Australian-accent recognition, neural text-to-speech and avatar-ready viseme output — with documented model lineage and no Chinese-origin weights in the production tree. It runs in Sydney or entirely on your hardware, with the audio path staying inside your perimeter.
How Camlin Speech maps against PSPF, FOCI and HCF →Heritage in high-security networks
Defence-sector operations
Years of production network-operations delivery inside a high-security defence-sector environment — the operational discipline behind the platform’s air-gapped deployment model. Details available under NDA as part of the assurance pack conversation.
Public-sector delivery
Transport NSW’s accessible booking service runs on this platform — thousands of monthly bookings, WCAG 2.1 AA, delivered on time. Read the case study →
Get the Sovereign Assurance Pack
We’ll respond within one business day with the pack and offer a 30-minute walkthrough with the deployment team.