Home / Deployment
The Same Engine, Wherever It Has to Run
Most AI redaction is a cloud service. That is a problem when the content is criminal-justice material, classified, or subject to a sovereignty requirement, because the determining question is not model quality. It is whether content crosses the boundary at all.
The Six
| Posture | Who holds the infrastructure | Who operates it |
|---|---|---|
| Shared SaaS | VIDIZMO | VIDIZMO |
| Dedicated cloud | VIDIZMO, isolated tenancy | VIDIZMO |
| Private cloud | You, in your own cloud subscription | You, or VIDIZMO by arrangement |
| On-premises | You, your data center, your hardware | You |
| Hybrid | Cloud application reaching on-premises systems | Shared |
| Air-gapped | You, disconnected from the internet | You |
Air-Gapped, and What That Actually Means
Plenty of vendors say "on-premises" and mean the application runs locally while the AI still calls a hosted API. That fails the requirement it was meant to satisfy.
In an air-gapped deployment the whole AI stack is local: language models through vLLM or Ollama, and local models for transcription, computer vision, OCR and PII detection. No content and no inference request leaves the deployment.
The deployment hosts its own models and its own supporting infrastructure. Integrations that reach external services are unavailable by definition, and identity federation resolves against a directory inside the boundary.
Containerized cognitive services
Short of full disconnection, cognitive services run in containers inside your own infrastructure, so capabilities that would otherwise call a cloud service operate without egress.
Does customer content train the models?
Whether customer content may be used for AI model improvement is a configurable setting, exposed through a consent app, so the position is recorded rather than assumed. Every AI procurement asks this question; the setting is what makes the answer verifiable rather than a promise.
Sovereign Regions
The platform connects to sovereign cloud regions rather than only the global one, so storage, cognitive services and identity resolve in-country.
Supported connection environments: Azure Global, Azure US Government, China, and German government cloud.
Scale and Resilience
A high-availability topology runs the web application across several servers behind a load balancer, with the database on availability groups holding replicas.
Also available: containerized deployment, bring-your-own-cloud, Azure and AWS marketplace listings, silent installer deployment, rolling application upgrade, zero-downtime database upgrade, backup and restore, and disaster recovery.
What Deployment Does Not Do
- The web application is the tier that scales out. Other services run as single instances per deployment, which shapes the topology.
- Each application instance carries its own license activation.
- Licensing verification requires outbound access independently of AI processing. It is disabled for disconnected deployments.
- In an air-gapped deployment, integrations that reach external services are unavailable by definition.
How Deployment Is Evaluated
- Six postures from shared SaaS to fully disconnected, running the same redaction engine.
- Air-gapped runs the entire AI stack locally — transcription, vision, OCR, PII and language models — with no outbound call.
- Cognitive services are containerizable inside customer infrastructure short of full disconnection.
- Sovereign connection environments: Azure Global, Azure US Government, China, German government cloud.
- Whether customer content trains models is a configurable, recorded setting rather than a contractual assurance.
- High availability scales the web tier behind a load balancer with database availability groups.
Tell Us Your Constraint
Sovereignty, classification, or a network that does not reach the internet. The answer is usually one of the six, and we will tell you which.