Agent Configuration

There are different options you can use to configure an agent and tailor it to your specific use case.

For more details, read our agent creation guide on how to build an agent.

You have the following configuration options to customize your agent:

Icon, Name, and Description

Short descriptive information to identify the agent and explain how it works to other users.

Property	Limit
Agent name	80 characters
Agent description	500 characters
Agent instructions	40,000 characters

Input Type

Agents support different input types that determine how they receive information.

Prompt (Default)

The chat input field you already know from normal chat. This lets you send any message to the agent and receive a response.

You can set conversation starters — saved prompts users can click instead of writing the first message. These help guide users and reduce the effort needed to get started. See Advanced Features for details.

Form

Forms collect information in a structured way, similar to a survey. This helps users understand what context is needed for a quality response and collects it in a standardized format the model can process more easily. See Form Fields.

Instructions

Describe what you want to achieve with this agent and define clear instructions. Include as many relevant details and as much background information as possible. This enables the agent to answer better and more closely to your expectations. Check out our agent creation guide and our prompting guide for more details.

Knowledge

Attach knowledge and files to your agent. You can either upload files from your computer or attach Knowledge Hub folders so the agent can reference a curated set of documents. The agent retrieves relevant passages from this knowledge and cites the source file, page, and location in its answers.

Source Access Restriction

By default, when your agent cites sources in its responses, users can click those references to open and view the original documents. If you need to protect sensitive source content while still allowing the agent to reference it, you can enable source access restriction.

When enabled, users see source references in responses but cannot click to open them. This is useful when:

• The agent needs access to confidential documents to provide accurate answers
• Users should receive information from sources without direct access to the underlying files
• You want to control document distribution while still leveraging the knowledge

This setting must first be enabled at the workspace level by an admin before it becomes available in the agent configuration. If you don't see this option, contact your workspace admin.

Tools

Tools extend what your agent can do beyond answering from its knowledge. Add any of the following:

Web Search

Let the agent search the internet for current information and cite the sources it finds.

Connector Actions

Connect your agent to external tools and services through MCP connectors. With a connector attached, your agent can perform actions such as:

• Create email drafts
• Update CRM entries
• Create support tickets
• Post messages to Slack
• And many more — see our integrations guides

Actions that change data run behind a confirmation gate so the user stays in control.

Folders

Attach Knowledge Hub folders to give your agent access to specific document collections without uploading the files directly.

Deep Research is only available in regular chats, not when using agents. To use Deep Research, switch to a regular chat session.

Model

Choose which model this agent will use. The agent is pinned to that model for every conversation. For help choosing, refer to our model guide.

Sharing

In the top-right corner you'll find options to share and use the agent. You can share it with your workspace or assign usage and editing permissions to specific groups or individuals.

Publishing

Changes to an agent's configuration are saved as a draft and do not affect users until you publish. Click Publish in the top-right corner to make the current draft the active version. Public agent pages always serve the active version.

For additional agent management features like labels, pinning, duplication, and owner transfer, see Advanced Features.