Resources
Configured capabilities available to Agents.
A Resource is a named capability that an Agent can use, such as a model, database, external API, browser, sandbox, or storage location. It keeps connection settings, authentication references, available actions, and access rules together. Agents bind to Resources by name; they do not contain connection details or secret values in their code.
Categories
| Category | Typical Resources |
|---|---|
| AI & Models | Logical Models and the connection Gateways through which they run |
| Apps & APIs | SaaS integrations, MCP Gateways, web access, and browsers |
| Data | Databases and query services |
| Storage | Artifacts, files, and managed secret capabilities |
| Compute | Sandboxes and other execution environments |
Credentials and Resources solve different problems. A Credential proves identity to an external system. A Resource defines what an Agent can do with that system. One Resource may reference a Credential, and the same Credential can support more than one Resource when Policy permits it.
Focused Resource views
The Console presents the same Resource abstraction through focused views. Gateways connect model providers. Models give Agents stable model identities on top of those Gateways. Services describe explicit HTTP API capabilities. MCP Gateways connect governed MCP capabilities. Tools are the model-facing capabilities pinned inside Agent packages. Sandbox Pools provide isolated execution capacity. UIs publish governed Agent-facing web interfaces. These views make different operational jobs legible without creating parallel infrastructure.
Choose a path
| Goal | Guide |
|---|---|
| Add or review a capability | Configure a Resource |
| Install a model-provider connection | Add and manage Gateways |
| Expose a Gateway model to Agents | Add and manage Models |
| Turn an HTTP API into Agent capabilities | Add and use Services |
| Review or connect an MCP integration | MCP Gateways |
| Write private provider integration code | Build a custom Gateway |
| Configure model routing, BYO access, or per-tenant pricing | Gateways and Models |
| Make a capability available to an Agent | Use Resources from Agents |
| Expose a safe model-facing capability | Build and use Tools |
| Publish a chat surface, dashboard, or interactive Agent application | Dynamic UIs |
| Set up authentication for an external service | Credentials |
| Understand an Agent's current bindings | Operate Agents |
Choose an interface
| Interface | Use it for |
|---|---|
| Console | Discovering, configuring, and reviewing capabilities |
| SDK | Declaring needs, building Tools, and invoking accepted Resources |
| CLI | Repeatable Resource, Gateway, Model, Memory, and binding administration |
| Platform API | Product integrations and custom administration |
The Resource CRN is its stable address. Display names make the Console easier to scan, while bindings and Policy use the exact CRN so similarly named capabilities cannot be confused. SDK code invokes the accepted Resource contract; the Console or Platform API creates, reads, enables, disables, and deletes tenant-managed Resource configurations.