# Agent **Agents** are intelligent task executors that combine knowledge, tools, and reasoning capabilities to understand user intent and automatically complete assigned tasks. They serve as the core automation engine in the Workforce Factory, capable of handling complex workflows and decision-making processes. ## What Are Agents? Agents are AI-powered systems that can: * **Understand Instructions**: Process natural language commands and extract actionable intent from complex requests * **Access Knowledge**: Query knowledge bases, documents, and databases to inform their decision-making * **Execute Actions**: Use tools and integrations to perform real-world tasks and operations * **Reason and Decide**: Make informed decisions based on available information and context * **Automate Workflows**: Transform manual processes into intelligent, automated systems ## Types of Agents The Workforce Factory supports two main types of agents: ### [Instruction-Based Agents](/workfx-1.1.x-english/workforce-factory/agent/instruction-based-agent.md) Driven by prompt instructions and natural language commands. These agents excel at: * Flexible expression and complex reasoning * Intelligent Q\&A with knowledge retrieval * Content creation with fact-checking * Automated report generation with data analysis ### [Flow-Based Agents](/workfx-1.1.x-english/workforce-factory/agent/flow-based-agent.md) Built through visual flow design for structured processes. These agents are ideal for: * Process control and task decomposition * Business process automation with data validation * Automated customer service with knowledge lookup * Systematic workflows with decision points --- # Agent Instructions: 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: ``` GET https://docs.workfx.ai/workfx-1.1.x-english/workforce-factory/agent.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.