The Agent Builder provides the instructions, knowledge, tools, and settings that control how an AI 2.0 Agent processes information and responds. Changes are saved to the selected draft and can be tested before the version is published.

This article explains how to configure AI Agent instructions, link Libraries and AI Tools, select a model, manage context and execution settings, and define the response format.

Prerequisites

Before configuring an AI 2.0 Agent, ensure that:

• The AI 2.0 Agent has been created.
• Your AI Agent Builder Access is set to Full Access.
• The required libraries, MCP Servers, and API Actions are available, if applicable.
• You have identified the AI Agent’s audience, responsibilities, restrictions, and fallback behavior.

For creation instructions, explore How to Create an AI 2.0 Agent in BoldDesk.

Open the AI Agent in Agent Builder

To open an AI Agent for configuration:

1. Go to AI Center > AI Agents.
2. Locate the required AI Agent.
3. Open More options.
4. Select Edit.

The Agent Builder displays the selected AI Agent version and the following configuration areas:

• Instructions
• Libraries
• AI Tools
• Settings

The right side of the page contains Playground, and the upper-right corner displays the version selector and Publish menu.

Configure AI Agent Instructions

Instructions define the AI Agent’s role, behavior, response style, restrictions, and responsibilities.

To configure instructions:

1. Open Instructions.

2. Enter or update the AI Agent’s instructions.

3. Organize the instructions into clear sections such as Role, Instructions, restrictions, and fallback behavior.

4. Click Save.

   

The page displays an unsaved-changes warning until the changes are saved. Click Discard to remove unsaved changes.

Generate Instructions Using AI

Use Generate using AI to create an instruction set through the Prompt Builder. The Prompt Builder asks questions about the AI Agent’s purpose, tasks, tone, boundaries, and expected behavior before generating the instructions.

To generate AI Agent instructions:

1. Open Instructions in Agent Builder.

2. Click Generate using AI.

3. In Prompt Builder, describe the AI Agent you want to create.

   Include information such as:

   • The AI Agent’s primary purpose.
   • The domain or tasks the AI Agent should handle.
   • The intended users.
   • The required tone and response style.
   • Any boundaries or actions the AI Agent must avoid.
   • The conditions that require escalation to a human support agent.

   For example: This AI Agent provides customer support for product setup, troubleshooting, and general product questions.

4. Respond to the follow-up questions from Prompt Builder. Prompt Builder may request additional information.

5. Review the generated instruction set in Prompt Builder.

6. If changes are required, enter additional guidance in Ask anything and submit the request.

7. When the generated instructions meet the intended requirements, click Use this prompt.

8. Review the generated content in the Instructions editor.

9. Modify any sections that do not match the AI Agent’s intended responsibilities, security requirements, or support workflow.

10. Click Save.

    

Improve Existing Instructions

Use Improve Instruction to improve the clarity, structure, formatting, and completeness of the instructions already available in the editor.

To improve existing instructions:

1. Open Instructions in Agent Builder.

2. Enter or review the existing instruction content.

3. Click Improve Instruction.

4. Wait while BoldDesk processes and improves the instructions.

5. Confirm that the Instruction improved successfully message appears.

6. Review the improved instructions directly in the editor.

7. Modify any instruction that does not match your organization’s requirements.

8. Perform one of the following actions:

   • Click Save to retain the improved instructions.
   • Click Discard to remove the unsaved changes.
   

Follow AI Agent Instruction Guidelines

Define the following information in the AI Agent instructions:

• The AI Agent’s purpose and audience.
• The requests the AI Agent should handle.
• The approved tone and response style.
• The knowledge sources the AI Agent should use.
• The actions the AI Agent can perform.
• The information the AI Agent must not disclose or confirm.
• The conditions that require a ticket or human-agent transfer.
• The fallback response when relevant information is unavailable.

Use these practices:

• Answer direct questions clearly before adding supplementary information.
• Use only verified information from linked libraries and approved data sources.
• Do not make unsupported statements about products, integrations, third-party systems, or internal processes.
• Do not confirm account ownership, subscription status, payments, purchases, invoices, or receipts without a secure verification workflow.
• Avoid PII guidance that rejects every message containing common contact details such as a name or email address.
• Define whether references or links should appear in customer-facing responses.

Link Libraries

Libraries provide approved information that the AI Agent can use when responding.

To link a library:

1. Open Libraries.
2. Click Link Library.
3. Select the required library.
4. Complete the linking process.
5. Confirm that the library appears in the linked libraries list.

To remove a linked library, locate it and click Unlink.

For library-management information, explore How to Add Knowledge Sources to BoldDesk AI 2.0.

Link AI Tools

AI Tools allow an AI Agent to retrieve external information or perform supported operations through MCP Servers and API Actions. Only MCP Servers and API Actions available under AI Tools can be linked to an AI Agent.

To link an AI Tool:

1. Open AI Tools.

2. Select the required connection type:

   • Click Link MCP Server to connect an MCP Server.

     

   • Click Link API Connection to connect an API Action.

     

3. Select the required MCP Server or API Connection.

4. If you selected an MCP Server, select the tools the AI Agent can use.

5. Complete the linking process.

6. Confirm that the linked MCP Server or API Action appears under AI Tools.

For setup instructions, explore further instructions on How to Create and Configure an MCP Server in BoldDesk and How to Create and Publish API Connections in BoldDesk.

Configure AI Agent Settings

Open Settings to configure the model, output length, tracing, context management, reasoning, execution controls, external tools, and response format.

The Settings page contains:

• Configuration
• Trace Logging
• Context Management & Reasoning
• Response & Execution Controls
• Tool Configuration
• Response Format

After changing a setting, click Save. Click Discard to remove unsaved changes.

Configure the Model and Output Length

Select a model and output-token limit appropriate for the complexity and expected response length of the AI Agent’s workflow.

Configure Trace Logging

Turn on Trace Logging to record selected AI execution details for troubleshooting and monitoring.

LLM Tracing

Tool Tracing

Configure Context Management and Reasoning

Expand Context Management & Reasoning to configure:

Choose values that provide sufficient context without adding unnecessary conversation history or unrelated knowledge.

Configure Response and Execution Controls

Expand Response & Execution Controls to configure:

Use a fallback instruction that directs the customer to an appropriate next step, such as creating a ticket, contacting the configured support email address, or requesting a human agent.

Configure External Tool Access

Expand Tool Configuration to configure:

Enable these settings only when external information is required for the AI Agent’s workflow.

Configure the Response Format

Expand Response Format and select the required output type:

Use Text for conversational workflows. Use JSON or Structured output when a system or orchestration rule must process specific output properties.

Save and Test the Configuration

After configuring the AI Agent:

1. Review the instructions, libraries, tools, and settings.
2. Click Save in each area containing changes.
3. Confirm that the unsaved-changes warning is no longer displayed.
4. Open Playground.
5. Test representative questions, alternate wording, missing-information scenarios, tool use, and applicable edge cases.
6. Update and retest the configuration when the results do not meet the intended requirements.

For detailed testing instructions, learn more on How to Test an AI 2.0 Agent in BoldDesk.

Assign and Deploy AI 2.0 Agents Across BoldDesk Channels

After the draft produces the expected results, publish the version and map it to the required channels.

For instructions, explore How to Assign and Deploy AI 2.0 Agents Across BoldDesk Channels.

Troubleshooting

Instructions Changes Are Not Retained

Confirm that you clicked Save. If the unsaved-changes warning remains visible, review and save the changes again.

The AI Agent Generates Irrelevant Responses

Review the instructions, linked libraries, context settings, grounded-response setting, and fallback instructions.

A Required Tool Is Not Available

Confirm that the MCP Server or API Action exists under AI Tools, is available for selection, and is linked to the AI Agent.

The AI Agent Cannot Find an Answer

Confirm that the required information exists in a linked library and is available to the AI Agent. Review the grounded-response and fallback settings.

The AI Agent Uses the Wrong Tool

Review the AI Agent instructions and linked tools. Clearly define the conditions under which each tool can be used.

Frequently Asked Questions

1. Can I generate AI Agent instructions automatically?
   Yes. Use Generate using AI, and then review and edit the generated instructions.

2. What is the difference between Libraries and AI Tools?
   Libraries provide knowledge. AI Tools retrieve external information or perform supported operations.

3. Can an AI Agent use both an MCP Server and API Actions?
   Yes. Link only the tools required for the intended workflow.

Related Articles

1. How to Test an AI 2.0 Agent in BoldDesk
2. How to Manage the AI 2.0 Agent Creation Page
3. How to Configure AI Agent Builder Access Permission