> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/cherry-studio/preview/agent.md). # Work - Agent An agent that lets AI autonomously execute tasks **Work**(also called **intelligent agent / Agent**) is a system in Cherry Studio that can **autonomously call tools, read and write files, and complete tasks across multiple steps** — and it is not the same thing as "Chat Assistant" (a role preset). The entry point is in **the \[Work] item in the left navigation bar**(not the top tab in the old tutorial). {% hint style="success" %} The easiest way: first tell the Agent what you want to accomplish, and let it check for itself which models / tools / knowledge bases / channels are still missing; if you need precise control, adjust them manually. {% endhint %}

[Work] interface: select the Agent, model, and working directory in order at the top, then enter the task below; manage tasks and working directories on the left

## What it can do * **Read and write files**: Give it a **Working directory**, and it can read, edit, and generate files in it. * **Call tools**: built-in tools, plus the [skills](/docs/en-us/advanced-basic/extensions/skills.md) and [MCP](/docs/en-us/advanced-basic/extensions/mcp.md) external tools. * **Multi-step reasoning / subtasks**: break down goals, dispatch sub-agents, and run background commands. * **Integrate automation**: with [Channels](/docs/en-us/advanced-basic/automation/channels.md) deployment to IM platforms, and use [Scheduled tasks](/docs/en-us/advanced-basic/automation/scheduled-heartbeat.md) scheduled execution. ## Quick Start 1. Open \[Work], choose an Agent; if there isn't one, click \[Add Agent] and create one in four steps (basic information / persona / skills / knowledge base). The built-in **Cherry Assistant** is ready to use. 2. When you need to work with local files, choose a **Working directory**; if no files are involved, just use the default workspace. 3. Describe the task with "what to deliver, what materials are available, and what counts as done". 4. View in the right panel **status / files / subtasks / message stream**; if developer mode is enabled, you can also view **call chain**. ## Permission Modes When the Agent performs file / command operations, you can choose **Confirm each time / Auto-accept edits / Smart approval / Plan only / Full access** Five permission modes, from the most cautious to the most permissive. Use the more permissive modes only when running unattended tasks (such as channels or scheduled tasks). *** ## Want to go deeper? See the advanced tutorial for full usage: * [Agent Workspace](/docs/en-us/advanced-basic/agent-workspace.md) — the complete workflow from creation to delivery * [Create an Agent and divide responsibilities with the model](/docs/en-us/advanced-basic/agent-workspace/create-agent.md) * [Working directories, tasks, and files](/docs/en-us/advanced-basic/agent-workspace/workspaces-tasks-files.md) * [Built-in tools, knowledge base, skills, and MCP](/docs/en-us/advanced-basic/agent-workspace/tools-knowledge-skills-mcp.md) * [Permissions, memory, and background tasks](/docs/en-us/advanced-basic/agent-workspace/permissions-memory-background.md) *** ### Get help and submit feedback If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) for the official channels provided. --- # 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.cherryai.com.cn/docs/en-us/cherry-studio/preview/agent.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.