Public cloud. Private cloud. On-premise. Air-gapped.
Saptiva AI runs wherever your compliance framework requires. The same applications, the same orchestration, the same audit surface — across every deployment mode. When the framework changes, the platform follows. You don't replatform.
Deployment mode is a runtime concern, not a product concern. The applications, the orchestration engine, the policy language, the audit surface — they are identical across public cloud, hybrid, on-premise, and air-gapped deployments. Only the compute placement changes.
Every Saptiva AI deployment sits in one (or more) of these four modes. FrIdA routes workloads across them according to the policy you author. A single customer deployment routinely runs workloads in multiple modes simultaneously, against different data classes.
Elastic compute for non-resident workloads.
Non-sensitive workloads, general-purpose tasks, bursting capacity, development and staging environments. Not suitable for regulated data flows in most LatAm jurisdictions.
FrIdA forbids dispatch of workloads carrying regulated data unless the cloud provider and region explicitly satisfy the policy.
In-country cloud for regulated workloads.
Regulated data at volume, multi-tenant banking workloads, KYC at scale, customer operations with data residency requirements. The primary deployment mode for most of our banking and insurance customers.
Residency enforced by architecture. Egress forbidden. Customer-managed encryption keys. Full audit trail retained in-country.
Customer data center, customer hardware.
Institutions with an on-prem mandate, regulated workloads that cannot leave customer-controlled infrastructure, governments, and the highest-sensitivity financial and healthcare data flows.
Network egress controlled at the customer's perimeter. Audit stream consumed locally. Model weights resident on customer hardware.
Disconnected environments, maximum isolation.
Defense, intelligence, critical infrastructure, the most regulated government and financial workloads. Environments where the connectivity requirement itself is a risk.
Zero external connectivity at runtime. Model and policy updates via authorized, signed offline transfer. Full audit surface available locally.
A single deployment typically uses more than one mode — different data classes routed to different environments by the policy FrIdA evaluates. Common routings across LatAm regulated enterprises.
Most enterprise AI platforms treat deployment mode as a rebuild event. Moving from cloud to on-prem means new code, new configuration, new audit surface, new certification. Saptiva AI was built from the start to treat mode as a runtime concern.
Update the policy file. FrIdA starts routing the affected workloads on-premise on the next dispatch. The application code does not change. The audit record remains continuous.
Author a country-specific policy extension. The same Studio applications deploy against local compute. Two countries, one codebase, two policy regimes.
FrIdA's compute target changes by configuration. Zero application rewrite. Zero model retraining. Audit record remains portable.
Install the air-gapped runtime at the customer site. Route the specific workload by policy. The other workloads are unaffected. The platform remains one platform.
Every deployment mode relies on infrastructure we do not sell. Our partners provide the hardware, the cloud capacity, and the in-country distribution. Saptiva AI orchestrates above them.
Hybrid rack you're still standing up. Sovereign region you're migrating to. Air-gapped cluster your compliance team insists on. Saptiva AI is already there. A Forward Deployed Engineer will respond within 48 hours.
Request a deployment review →