For the complete documentation index, see llms.txt. This page is also available as Markdown.
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).
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.
[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 and MCP external tools.
Multi-step reasoning / subtasks: break down goals, dispatch sub-agents, and run background commands.
Integrate automation: with Channels deployment to IM platforms, and use Scheduled tasks scheduled execution.
Quick Start
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.
When you need to work with local files, choose a Working directory; if no files are involved, just use the default workspace.
Describe the task with "what to deliver, what materials are available, and what counts as done".
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 — the complete workflow from creation to delivery
If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions for the official channels provided.
