Inside your cloud.
Work within your tenancy and approved services. Define which model endpoints can receive information and how requests are treated.
Deployment
Your environment sets the terms.
Bring AI to the infrastructure your work requires. Shape the deployment around information residency, connectivity, performance and the way your team operates.
Alongside your systems.
Keep processing close to private sources on customer-controlled infrastructure. Plan capacity, access and operations together.
Within an isolated environment.
Design for local processing where external connections are restricted. Account for model delivery, updates and the complete operating environment.
Deployment patterns
Runs where your constraints live.
The same boundary architecture deploys from approved cloud through fully air-gapped environments. Pilot deployments are scoped to your perimeter.
Requests cross to allowlisted external models, after the boundary has transformed them.
For teams already using frontier models under contract.
From architecture to operation
The right fit.
For your estate.
We work through the practical questions with you: where the information lives, which services are permitted, what the workload needs and who operates it.
Information residency
Specify where source material, derived data and decision records are stored. Define the information permitted to cross between environments.
Models and capacity
Evaluate the workload, expected volume and quality requirements. Select the model and infrastructure against the actual task.
Ownership and operations
Agree access controls, key management, retention, monitoring and the people responsible for running the system.
Product and deployment considerations
| Product | Approved cloud | Private cloud / VPC | On-prem / edge | Isolated / air-gapped |
|---|---|---|---|---|
| BoundSense | Designed | Designed | Designed | Demonstrated (synthetic Local-Only policy model) |
| Cortex Assist | Designed | Available in pilots | Available in pilots | Designed |
| Cortex Extract | Designed | Available in pilots | Available in pilots | Designed |
| Cortex Voice | Not offered | Designed | Available in pilots (local processing) | Designed for isolation |
| Forge | Designed | Designed | Available in pilots (training) | Designed |
| Forge Private Distributed Evaluation | Planned | Planned | Planned | Planned |
| Cortex Governed Distributed Retrieval | Planned | Planned | Planned | Planned |
| AxonCX | Available in pilots | Designed | Designed | Not suited (external channel connectors) |
| Axon Live Agent | In development | In development | Designed | Not planned |
Environment-specific packaging, integration and operational requirements are established during scoping. External-channel connectors require the relevant platform connections.
A first conversation
Start with
one workflow.
Tell us the task and where the information must stay. We'll show a relevant example and discuss whether a scoped pilot makes sense.
Request a demopilot@kordane.ai