Create a prompt agent

Level: beginner

This article explains how to create a new Prompt Agent in Creatio AI Studio step by step. In general, prompt agents are the easiest to create. You only need to describe what the agent needs to do in plain text. You can also enhance the agent with additional tools, skills, and knowledge sources as well as specify its triggers, version the agent, deploy it to different envirnoments. After the agent is created, you can observe its behavior using a full-fledged analytics suite and govern the agent via dedicated policies.

Example

Create an FAQ agent that answers common questions based on the knowledge library in the web chat. Users must be able to upload files.

Log in to Creatio AI Studio.
Go to Managed Agents group → Agents. This opens a page.
Click New → select the required agent type. Select "Personal" if you only need an agent for personal use, select "Enterprise" if the agent must be visible and useable across your organization. For this example, select "Enterprise." This opens a window.
Select Prompt Agent Designer.
Click Next.

Fill out the agent identity fields.

Field	Field value
Name	Human-readable name for the agent. Use short, clear names that reflect the agent's main goal. For example, "FAQ Agent."
Code	Technical ID used by Creatio and the LLM. Creatio generates this value automatically based on the name you provide, for example, "builder-faq-agent-c0f758." You can edit the code manually if needed.
Description (optional)	Plain-text summary of what the agent does and when to use it. For example, "Answers ."

Click Next.
Click Create. This opens a page on the Build → Agent tab.

Fill out the Instructions section.

Field	Field value
System prompt	Internal instructions sent to the model at runtime. Use this field to define the agent's role, behavior, and constraints. For example, "You are an FAQ agent who helps users find answers to questions about the product. Use only information from the connected knowledge base. Respond briefly, clearly, and in the user’s language. If there is no exact answer, do not make one up. Indicate that no information was found and suggest that the user contact support. Whenever possible, include a link to the source."
Welcome title	Heading displayed when a chat conversation starts. For example, "Do you have any questions about the company knowledge?"
Welcome Message	Opening greeting used when a chat or voice conversation starts. For example, "Hello! How can I help you today?"
Model	The large language model (LLM) the agent uses. Set to GPT-5.2 out of the box. Click the model name to choose a different model.
Temperature	Controls response randomness on a scale from 0 to 2. A higher value produces more varied responses; a lower value produces more focused, deterministic ones. The default value is 1.0.
Memory	Toggle to enable session-level memory so the agent can retain context across turns in a conversation. Enabled by default. Expand Memory settings to configure memory scope and retention behavior.

Go to Build → Tools tab to select which registered tools the agent is allowed to call.
1. Review the Tool library. The panel shows all available tools grouped by type:
  - Available — all tools registered in Creatio.
  - Enabled — tools currently active for this agent.
  - HTTP — custom HTTP-based tools.
  - MCP — tools registered via the Model Context Protocol.
  - Generative UI — tools that render dynamic UI components during a conversation.
2. Enable tools by selecting the checkbox next to each tool name. For this example, add the File search tool.
3. Click Add HTTP tool or Add MCP server to register a new external tool. Built-in model tools, such as Web search, are listed separately and can be enabled or disabled independently.
Go to Build → Skills tab to attach Skills to the agent.
1. Select an existing skill from the list in the Attach Skill field. Once attached, the skill's files, scripts, references, and assets are displayed in the panel. For this example, do not attach any skills.
  
  If the agent's active deployment is out of date after a configuration change, a Deployment update required warning appears in the skill panel. Publish a new version to resolve the warning.
Go to Build → Knowledge tab to attach knowledge sources the agent can query for context.
1. Open the Knowledge Sources menu.
2. Select one or more knowledge sources from the list. For this example, select your knowledge base.
Once attached, the agent uses the indexed content from the selected knowledge sources to generate more accurate and context-aware responses.
Go to Configure → Profile tab to set how the agent is presented to users in chat.

Field
Field value
Description
Short explanation shown in agent cards and compact previews.
Full description
Longer agent description, operating mode, and guidance for users.
Go to Configure → Channels tab to bind channels to the agent.
1. Click Add Channel to create a new channel, or click Bind Existing to link a channel that is already registered in Creatio. For this example, select the "Web chat" channel.
2. Review the channel summary widgets: Bound channels, Active, and Voice.
The agent is not reachable by end users until at least one channel is bound. You can test the agent in the Live preview panel regardless of channel configuration.
Go to the Preview panel on the right to test the agent.
1. Select the target environment, for example, "Sandbox," in the Environment field.
2. Type a message in the Send a message… area and press Enter.
3. Review the model's response. Toggle Show trace on to inspect the full reasoning trace.
Click Publish in the top right.
Click Deploy in the top right and select the target environment.

Field	Field value
Description	Short explanation shown in agent cards and compact previews.
Full description	Longer agent description, operating mode, and guidance for users.

As a result, Creatio will publish the agent and change its status from Draft to the active version. The published agent becomes available to users of the corresponding environment through the assigned channels.

See also​

See also