Get startedConnect owned hardware for local inference, private processing, and device-backed workloads.
Source reviewed 2026-09-23. Availability depends on your installation, permissions, and compatible runtimes. A supported path is not a guarantee of model quality or production readiness.
Start here
What you need to know first
Check the inputs below before starting. If you are new, begin with the first-project guide. A dataset holds media and labels; a model produces results; a deployment makes a selected model version callable. Creating one does not create the others.
Bring these inputs
- A device identity and scoped credential
- Hardware capability and compatible runtime
Expected output and limits
- A registered device target
- Heartbeat, assignments, logs, and locally produced results
Core workflow
- 01
Register the device
Create a device identity and install the Score edge agent with its scoped credential.
- 02
Verify capabilities
Report architecture, accelerators, runtime versions, storage, and heartbeat health.
- 03
Assign work
Select the device for an eligible deployment or workload.
- 04
Operate safely
Monitor heartbeat and tasks, rotate credentials, or revoke access when the device leaves service.
What this surface supports
- Local inference
- Private data paths
- Device-backed workloads
- Heartbeat and capability reporting
Expert section
Contracts, signals, and failure modes
Use this section when you are defining acceptance criteria, automating the surface, or reviewing whether its output is safe to promote downstream.
Expert release checklist
- Inputs and dependencies are pinned to immutable versions.
- Acceptance metrics include critical classes and operating slices.
- Failure, retry, cost, and rollback behavior are understood.
- The resulting artifact has an owner and a downstream review path.