Agent Workspace

A complete workflow from creation to delivery

An Agent is suited for tasks with clear goals, requiring tools or files, and possibly spanning multiple steps. The entry point is the left sidebar [Work], not the top tab in the old tutorial.

The easiest way to configure it is to first tell the Agent what you want to accomplish, then let it check which models, tools, knowledge bases, or channels are missing. When precise control is needed, open the Agent editing window or [Settings] to adjust manually.

The working directory, permissions, and completion criteria run through the entire task; when changes are needed, return to the planning stage to confirm them again.

What makes up the workspace

Section	Effect	When to pay attention
Agent	Save roles, models, prompts, and capabilities	When the same kind of work needs to be repeated
Task	A continuous work record	Open a separate task for each goal to keep the context.
Working directory	The range of files the Agent can directly handle	File tasks such as code, material organization, and document generation
Input area	Send goals, attachments, and call tools	Start a task or add requirements
Right-side panel	View status, files, subtasks, and message stream	Track long tasks, check deliverables, or troubleshoot

Before starting a task, first confirm the Agent, model, working directory, and right-side panel.

Start a task

1

1. Open [Work] and select an Agent

If you already have a suitable Agent, select it directly; if not, click [Add Agent] and create one in four steps: basic information, persona, skills, and knowledge base.

2

2. Select the working directory

When you need to process local files, choose the directory for this task; if no files are involved, you can use the default workspace created by the app. One task corresponds to one workspace, avoiding the Agent from searching back and forth among unrelated directories.

3

3. Describe the task in terms of results

Tell the Agent what to deliver, what materials it can use, what restrictions there are, and what counts as done. For example:

Read the meeting notes in the current directory, organize the decisions, owners, and deadlines, and generate action-items.md. Do not modify the original files.

4

4. Check the process and deliverables in the right-side panel

[Status] shows active tasks, sub-agents, workflows, and background commands; [Files] lets you preview and edit text deliverables; after enabling Developer Mode, you can also view the [call chain].

API Gateway tip

Agent operation depends on Cherry Studio's API Gateway. When the gateway is not enabled, the app will prompt [Enable and start]; you can also go to [Settings] → [API Gateway] to check the port, running status, and whether local security software is blocking it.

The API Gateway is a runtime dependency for the Agent, but that does not mean the interface must be exposed to the network. Keep the default local use; only when you explicitly want other programs to call it do you need to copy the URL and API key.

One Agent or multiple Agents

• Same role, same set of capabilities, but different tasks: reuse one Agent and create multiple tasks.
• Different roles, different material scopes, or different permissions: split into multiple Agents.
• One goal requires parallel research or multi-step collaboration: first let one Agent use sub-agents or a workflow; there is no need to manually create many Agents right away.

User case: organizing project materials

A product manager puts the requirement spec, interview notes, and competitor materials in the same directory, creates a "Requirements Organization" Agent, binds the product knowledge base, and uses [Step-by-step confirmation] permission. The Agent first reads the materials, then writes the requirements list and questions to be confirmed into a new file. The product manager directly revises the text in the right-side [Files], and the original materials remain unchanged.

Why can't the Agent see the capability I just bound?

Edits to the Agent are saved automatically. The response currently being generated will not be interrupted; changes to models, skills, MCP, and knowledge bases will take effect starting with the next message. If it still does not appear, first confirm that the capability is enabled, then send a new message.

Will deleting the working directory also delete the disk files?

When deleting a working directory in the task list, only the directory record in Cherry Studio and the task records under that directory will be removed; the actual directory on disk will not be deleted. File operations performed by the Agent during task execution are still subject to the selected permission mode.