Agents are in the beta phase of development and may not be available on your enrollment. Functionality may change during active development.
With Agents, developers can build, configure, and ship pro-code agents in Foundry. An agent is custom logic written in a Foundry code repository. It uses a large language model (LLM) to reason over a prompt and call tools that read and write data in your environment.
Agents authenticate against the Ontology SDK (OSDK), Ontology MCP (OMCP), and Palantir MCP with scoped permissions out of the box. You do not need to pass a client ID and secret to call tools. After you publish an agent, you can call it from Workshop or the Ontology SDK with no additional configuration.
For common ways to use agents, such as reading and writing Ontology data, building platform resources, and migrating legacy systems, review our use cases documentation.
An agent is defined in a code repository created from the agent template. The template includes:
When you publish the agent, Foundry registers it with an Ontology binding and an agent API name. The published agent is exposed as an asynchronous function. We recommend triggering agents from Automate, but you can also call them from Workshop, the Ontology SDK, and Ontology actions.