Deployment options

AI deployment options.
Including air-gapped environments.

Deploy DT on your infrastructure, including air-gapped environments, or choose a DT-hosted arrangement. Place the application, inference, data, and tools where the work requires them, with clear operating ownership.

Customer-hosted or DT-hosted

Air-gapped deployment available

Explicit operating responsibilities

01 / Hosting arrangements

Two ways to host. Separate decisions underneath.

Choose who runs the platform and where its components live. Either arrangement can serve enterprise or government teams; the right choice follows your infrastructure and operating needs.

01

Customer-hosted

Run the application, durable state, workers, and configured execution services on infrastructure you control. The documented Docker Compose stack provides a starting point. Production sizing, hardening, networking, and operational support are scoped for your environment.

02

DT-hosted

Have DT operate the platform under an agreed hosting and support arrangement. We confirm infrastructure location, connectivity, enabled features, data handling, and operating responsibilities during scoping. Discuss dedicated or organization-specific requirements with us.

Scroll the table horizontally to compare arrangements.

What runs where, and who manages it
Part of the systemCustomer-hostedDT-hosted
Application and stateCustomer-controlled infrastructure. Customer operates it, with DT implementation or support as agreed.DT-operated infrastructure. Location, organization setup, and service responsibilities are agreed in scope.
Model inferenceConfigured provider or accessible model endpoint; customer manages credentials and network approval.Agreed model endpoints and credentials, configured by platform operators. Inference may run separately from the application.
Files and working dataConfigured customer storage. Customer owns storage access, retention, backup, and recovery operations.Storage and operational handling defined in the hosting arrangement. Customer defines information policy and permitted use.
Tool and computer executionConfigured workers, browser services, and optional sandboxes in the approved topology. Paired computers require separate access decisions.DT-managed execution services as agreed. Connected apps, private systems, and paired computers retain their own boundaries.
Connected systemsCustomer authorizes accounts, scopes, and destinations. External systems and model providers process requests under their own terms and configuration.

02 / Models and network paths

Put inference and tools in the deployment plan.

Platform operators configure providers, model endpoints, routing, and applicable fallback behavior. The model used for an agent can differ from the services used for browsing, document interpretation, or generated media.

01

Model choice requires validation

We assess the selected endpoint against the intended workflow, tool use, capacity, and network requirements. An accessible endpoint is not evidence that every platform feature works with it.

02

Connections define data movement

Document the information sent to models, integrations, email, browser services, and telemetry. Keeping the application on customer infrastructure does not by itself keep all traffic within that boundary.

03 / Air-gapped AI deployment

Run the work inside your boundary.

DT supports air-gapped deployment. The supported configuration places the platform, model inference, and the tools needed for the workflow inside the isolated environment. Select the available capabilities around those internal services.

01

Use internal inference and tools

Configure model access, API and MCP connections, identity, storage, execution, and logging within the boundary. External SaaS connections are replaced with internal alternatives or left disabled in the air-gapped configuration.

Explore internal integrations
02

Plan disconnected operations

Establish installation artifacts, software and model updates, malware definitions, backup and recovery, and maintenance access. Document the dependencies and test representative work in the target configuration.

03

Choose the implementation support

Use platform documentation with your own team, or bring in DT engineers for initial consulting, deployment, and integration. Independent advice can also evaluate other approaches.

Explore air-gapped implementation services

Explore the components and boundaries in our air-gapped AI reference architecture, then use the model update lifecycle guide to plan controlled changes. These educational guides provide evaluation questions to apply to your DT configuration.

04 / Getting to production

Agree the handoff before rollout.

A working installation is the beginning of an operating service. Establish the roles, evidence, and support needed to sustain it.

01

Customer responsibilities

Set information-handling rules, authorize connections, provide infrastructure and identity access where required, and designate administrators and reviewers.

02

Implementation and ongoing support

Define acceptance tests, monitoring, incident escalation, upgrades, recovery, and training. Software, hosting, implementation, and support are scoped as distinct commercial components.

Plan an engagement

Review Security & Governance with the people responsible for your deployment.

Next steps

What will your team build?

Explore the platform around your systems and workflows. Your team can lead implementation, with DT engineering or independent consulting available when you need it.