Create and Orchestrate an Agent

The Agent editor separates core orchestration from final presentation: the main area configures the prompt, variables, Knowledge Base, and capabilities; Agent Settings configures the name, model, conversation presentation, and iteration cap.

Create an Agent

1. Navigate to Apps, select Create App > Agent.
2. Fill in the name. The name can be 1-100 characters; the description up to 500 characters.
3. On the orchestration page, select Agent Settings in the top-right corner, choose the model, and configure the name, icon, opening message, suggested questions, and visibility.
4. Set visibility to Private or Team.

Write the Prompt and Variables

1. In the Prompt, specify the role, task, constraints, tool usage conditions, and failure handling.
2. Type { to open the variable selector. {query} is the current user message.
3. In Variables, add user input fields. Variable names can be up to 50 characters; you can configure the display name, required, hidden, default value, options, numeric range, or maximum length.
4. Fill in the variables in the preview on the right and confirm the substitution result.

Link a Knowledge Base

1. In the Knowledge Base area, select Add.
2. Select a Knowledge Base and a vector, fulltext, or hybrid retrieval mode.
3. Set Top K (1-100, default 5) and the threshold (0-1, default 0.3).
4. Set the overall RAG mode: Agentic RAG, Naive RAG, or Off.

Add Tools and Capabilities

In the Tools area, select a built-in tool, custom tool, MCP, or Skill. When a tool shows "Configuration needed", go to Capabilities first to complete the credentials. When enabling attachments, user input requests, memory, image generation, or video generation, check the corresponding limits and default model in each case.

Save, Debug, and Publish

1. Select Save. Validation errors list the specific fields.
2. In Debug & Preview, send questions that cover both normal and failure paths.
3. When tools are present, verify tool parameters, failure prompts, and max-iteration termination behavior.
4. Select Publish. After publishing, you can open the Public Page, Embed, and Access API.

FAQ

• Empty model list: The team has no authorized chat model, or the model is disabled.
• Tools are not called: Check the model's function-calling capability, whether the tool is enabled, and whether the prompt defines the calling conditions.
• Publish fails: Confirm you have the publish permission, and that the model, variable references, and capability configuration are valid.
• Public page inaccessible: Confirm the Agent is published; private/team visibility is still affected by sign-in and team access control.