> For the complete documentation index, see [llms.txt](https://docs.peoplelogic.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.peoplelogic.dev/guides/getting-started-with-the-talent-agent-sdk/classes-of-agents.md). # Classes of Agents The Talent Agent SDK makes a distinction between two different classes of agents - the coordinator agent (or orchestrator) and the worker agents. This separation of concerns allows you to build highly specialized teams of agents by easily adding new agents to a team without changing your orchestration. When using the SDK, all agents will automatically be registered as Spring Beans. This means they can be autowired into other components (such as your tools) or other service layers that you may have within your application. ### Coordinator Agents The `CoordinatorAgent` implementation defines the agent that will handle assignment of tasks to the workers. In addition to implementing the CoordinatorAgent interface, you also need to be sure to name your agent bean the `coordinatorAgent`. {% hint style="info" %} The same agent can be used as both a coordinator and worker, you simply need to implement both interfaces. {% endhint %} This agent also handles verification of inputs for the requested task or conversation to minimize back and forth. Finally, in addition to assigning tasks and managing orchestration, the CoordinatorAgent can also answer simple questions about the team or if it is also a worker agent, it can handle the task itself. Finally, the CoordinatorAgent has it's own pre-configured `ToolProvider` that only executes when you use it also as a WorkerAgent. It will automatically pick up any `Tools` that you define on the agent. We'll talk more about Tools in a later section. ### Worker Agents Put simply, the `WorkerAgent` implementations are responsible for receiving a task and doing the work. These agents typically have their own personality and instructions along with a specialized `SystemMessage` and `Tools` that help them get things done. As part of the SDK, we have included several built-in Talent-related agents that you can enable, customize and include as part of your team. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.peoplelogic.dev/guides/getting-started-with-the-talent-agent-sdk/classes-of-agents.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.