Advanced capability map

Choose current capabilities based on your goal

The advanced tutorials are not listed one by one according to the Settings menu, but instead start from “what do you want to accomplish.” First choose the closest goal, then enter the corresponding tutorial.

First use the main entry point to complete the smallest task; once the result is stable, then add the knowledge base, skills, MCP, channels, or scheduled tasks.

When you need to configure a set of tutorials, channels, scheduled tasks, or extended capabilities, prioritize telling the Agent your goal in [Work]. The Agent can help determine what is missing and guide you through common setup. When you need to verify accounts, keys, or exact parameters, then go to [Settings] to adjust them manually.

The left-side launcher provides nine main entry points; choose the one closest to your task to begin.

Diagram note: first choose the main entry point based on the goal, then add skills, MCP, channels, or scheduled tasks once the process is stable.

Choose an entry point by goal

What do you want to accomplish	Recommended entry	Capabilities to be used
Compare multiple answers, organize long discussions	[Chat]	Multiple models, message branches, context, citations, and outputs
Process files or complete multi-step tasks	[Work]	Agent, working directory, tools, permissions, and status panel
Ask questions reliably using your own materials	[Knowledge Base] → run retrieval tests, then bind to Agent	Files/web pages/notes, RAG, retrieval scope
Generate illustrations from articles or edit images	[Drawing], or enable [Generate Image] in Agent	Templates, reference images, local edits, enhancement
Translate text, screenshots, or long documents	[Translation]	OCR, document processing, history, and favorites
Save drafts and continue refining them	[Notes]	Markdown, search, export, add to knowledge base
Open commonly used web apps	[Mini Programs]	Built-in web tools and added sites
Browse, preview, and organize local files	[Files]	File list, preview, and follow-up processing
Connect external tools or establish fixed workflows	Let the Agent judge first, then check in [Settings]	Skills, MCP, built-in tools
Use the Agent from external platforms	First let the Agent guide the setup in [Work]	Channels, allowed scope, permission mode
Generate daily reports or reminders on a schedule	Get the Agent working first, then create [Scheduled Tasks]	Agent, working directory, channels, run history
View materials and tasks at the same time	Right-click tab → [Open in New Window]	Multiple windows, pinned tabs, global search
Manage programming command lines	Launcher [Coding Partner]	Code CLI, model connection, directory, and terminal
Let local programs call the model or troubleshoot issues	[Settings] → [API Gateway] / [System]	Compatible API, call chain, developer mode

Recommended learning order

1

1. First master the Agent workspace

Learn how to create Agents, choose a working directory, and understand model roles and permissions. The later extensions, automation, and project examples are all built on this.

2

2. Then connect materials and capabilities

Use the knowledge base for long-term materials, skills for repeated methods, and MCP for external systems. Add only one capability at a time and verify it with a small task.

3

3. Finally run automatically or connect externally

After manual results are stable, configure channels, scheduled tasks, Code CLI, or external APIs. This makes it easier to identify which link is causing problems when something goes wrong.

Read by module

Advanced chat

Multiple models, branches, context, and outputs

Agent Workspace

From configuration and execution to file delivery

Knowledge and content workflow

Knowledge base, notes, drawing, and translation

Extend the Agent's capabilities

Skills and MCP

Automation and external reach

Channels, scheduled tasks, and heartbeat

Efficient workspace

Multiple windows, productivity tools, and search

Development and diagnostics

Code CLI, API Gateway, and call chain

Application examples

Nine complete workflows

Working directories, MCP, channels, and high-privilege mode all expand the range of data the Agent can access. Only provide the directories, tools, and accounts needed for the current task, and do not place API keys, bot secrets, or private materials into public conversations or screenshots.