# (legacy) Use generative AI-powered self-service with Connect AI agents
<a name="generative-ai-powered-self-service"></a>

**Important**  
Legacy self-service is not receiving new feature updates. For new implementations, we recommend using [agentic self-service](agentic-self-service.md), which provides autonomous multi-step reasoning, MCP tool integration, and continuous conversations.

**Tip**  
Check out this course from AWS Workshop: [Customizing Connect AI agents Self-Service](https://catalog.workshops.aws/amazon-q-in-connect/en-US/customizing-amazon-q-in-connect-self-service). 

Connect AI agents supports customer self-service use cases in chat and voice (IVR) channels. It can: 
+ Answer customer questions.
+ Provide step-by-step guidance.
+ Complete actions like rescheduling appointments and booking trips.

When customers need additional help, Connect AI agents seamlessly transfers them to agents while preserving the context of the full conversation.

**Topics**
+ [Default system tools](#default-system-actions-for-ai-agents-self-service)
+ [Set up self-service](#enable-self-service-ai-agents)
+ [Custom actions for self-service](#custom-actions-for-connect-ai-agents-self-service)
+ [FOLLOW\$1UP\$1QUESTION tool](#follow-up-question-tool)

## Default system tools
<a name="default-system-actions-for-ai-agents-self-service"></a>

Connect AI agents comes with the following built-in tools that work out-of-the-box:

1. **QUESTION**: Provides answers and gathers relevant information when no other tool can directly address the query.

1. **ESCALATION**: Automatically transfers to an agent when customers request human assistance.
**Note**  
When ESCALATION is selected, it takes the **Error** branch of the **Get customer input** block.

1. **CONVERSATION**: Engages in basic dialogue when there's no specific customer intent.

1. **COMPLETE**: Concludes the interaction when customer needs are met.

1. **FOLLOW\$1UP\$1QUESTION**: Enables more interactive and information-gathering conversations with customers. For more information about using this tool, see [FOLLOW\$1UP\$1QUESTION tool](#follow-up-question-tool).

You can customize these default tools to meet your specific requirements. 

## Set up self-service
<a name="enable-self-service-ai-agents"></a>

Follow these steps to enable Connect AI agents for self-service:

1. Enable Connect AI agents in your Amazon Lex bot by activating the [AMAZON.QinConnectIntent](https://docs.aws.amazon.com/lexv2/latest/dg/built-in-intent-qinconnect.html). For instructions, see [Create an Connect AI agents intent](create-qic-intent-connect.md).

1. Add an [Connect assistant](connect-assistant-block.md) block to your flow.

1. Add a [Get customer input](get-customer-input.md) block to your flow to specify:
   + When Connect AI agents should begin handling customer interactions.
   + Which types of interactions it should handle.

   For instructions, see [Create a flow and add your conversational AI bot](create-bot-flow.md).

1. (Optional) Add a [Check contact attributes](check-contact-attributes.md) block to your flow and configure it to determine what should happen after Connect AI agents has completed its turn of the conversation: In the **Attribute to check** section, set the properties as follows:
   + Set **Namespace** = **Lex**
   + Set **Key** = **Session attributes**
   + Set **Session Attribute Key** = Tool

   Connect AI agents saves the selected tool name as a Lex session attribute. This session attribute can then be accessed by using the **Check contact attributes** block. 

1. (Optional) Define routing logic based on the tool selected by Connect AI agents:
   + Route COMPLETE responses to end the interaction.
   + Route custom tool responses (like TRIP\$1BOOKING) to specific workflows.

   The following image shows an example of how you can make a routing decision based on what Connect AI agents decides.  
![\[Contact routing based on ai agent tool selections for COMPLETE and TRIP_BOOKING paths.\]](http://docs.aws.amazon.com/connect/latest/adminguide/images/generative-ai-powered-self-service-q-3.png)

## Custom actions for self-service
<a name="custom-actions-for-connect-ai-agents-self-service"></a>

You can extend Connect AI agents's capabilities by adding custom tools. These tools can:
+ Surface next best actions for customers.
+ Delegate tasks to existing Amazon Lex bots.
+ Handle specialized use cases.

 When adding a custom tool to your AI prompt: 
+ Include relevant examples to help Connect AI agents select appropriate actions.
+ Use the [Check contact attributes](check-contact-attributes.md) block to create branching logic.
  + When you configure **Check contact attributes**, in the **Attribute to check** section, enter the name of your custom tool.

  The following image shows a custom tool named TRIP\$1BOOKING is specified.  
![\[A custom tool named TRIP_BOOKING in the Check contact attributes block.\]](http://docs.aws.amazon.com/connect/latest/adminguide/images/trip-booking.png)

### Example: Disambiguate the customer intent
<a name="disambiguate-the-customer-intent"></a>

You can create a generative AI assistant that gathers information before routing to an agent. This requires:
+ No knowledge base configuration.
+ Simple instructions to collect information.
+ Step-by-step guides to present the information to the agents. For more information, see [Display contact context in the agent workspace when a contact begins in Amazon Connect](display-contact-attributes-sg.md).

Following is an example tool definition for disambiguation. You can remove all default tools except CONVERSATION and add one new custom tool called HANDOFF:

```
tools:
- name: CONVERSATION
  description: Continue holding a casual conversation with the customer.
  input_schema:
    type: object
    properties:
      message:
        type: string
        description: The message you want to send next to hold a conversation and get an understanding of why the customer is calling.
    required:
    - message
- name: HANDOFF
  description: Used to hand off the customer engagement to a human agent with a summary of what the customer is calling about.
  input_schema:
    type: object
    properties:
      message:
        type: string
        description: Restatement to the customer of what you believe they are calling about and any pertinent information. MUST end with a statement that you are handing them off to an agent. Be as concise as possible.
      summary:
        type: string
        description: A list of reasons the customer has reached out in the format <SummaryItems><Item>Item one</Item><Item>Item two</Item></SummaryItems>. Each item in the Summary should be as discrete as possible.
    required:
    - message
    - summary
```

### Example: Recommend an action for a customer
<a name="recommend-action-for-an-end-customer-to-take"></a>

 You can configure next best actions in Amazon Connect by using flows. You can also configure automated actions and create step-by-step guides to provide UI-based actions to customers. For more information, see [Step-by-step Guides to set up your Amazon Connect agent workspace](step-by-step-guided-experiences.md).  Connect AI agents saves the selected tool name as a Lex session attribute. The attribute can then be accessed by using the **Check contact attributes** flow block.  

Here's an example tool definition for booking a trip:

```
-name: TRIP_BOOKING
  description: Tool to transfer to another bot who can do trip bookings. Use this tool only when the last message from the customer indicates they want to book a trip or hotel.
  input_schema:
    type: object
    properties:
      message:
        type: string
        description: The polite message you want to send while transferring to the agent who can help with booking.
    required:
    - message
```

When using the **Check contact attributes** flow block to determine which tool Connect AI agents has selected, you can make branching decisions to select the relevant step-by-step guide for that user. For example, if a customer wants to book a trip during a self-service chat interaction, you can: 
+ Match the TRIP\$1BOOKING tool response in your flow.
+ Route to the appropriate step-by-step guide.
+ Display the step-by-step interface directly in the customer's chat window.

 For more information about implementing step-by-step guides in chat, see [Deploy step-by-step guides in Amazon Connect chats](step-by-step-guides-chat.md).

## FOLLOW\$1UP\$1QUESTION tool
<a name="follow-up-question-tool"></a>

The FOLLOW\$1UP\$1QUESTION tool enhances Connect AI agents self-service capabilities by enabling more interactive and information-gathering conversations with customers. This tool works alongside the default and custom tools. It helps collect necessary information before determining which action to take.

The following code shows the configuration of the FOLLOW\$1UP\$1QUESTION tool.

```
- name: FOLLOW_UP_QUESTION
  description: Ask follow-up questions to understand customer needs, clarify intent, 
and collect additional information throughout the conversation. Use this to gather 
required details before selecting appropriate actions.
  input_schema:
type: object
properties:
  message:
    type: string
    description: The message you want to send next in the conversation with the 
      customer. This message should be grounded in the conversation, polite, and 
      focused on gathering specific information.
required:
  - message
```

The FOLLOW\$1UP\$1QUESTION tool complements your defined tools by enabling Connect AI agents to gather necessary information before deciding which action to take. It's particularly useful for:
+  **Intent disambiguation**

  When the customer's intent is unclear, use this tool to ask clarifying questions before selecting the appropriate action.
+ **Information gathering**

  Collect required details for completing a task or answering a question.

### Example FOLLOW\$1UP\$1QUESTION use case
<a name="follow-up-question-tool-use-case"></a>

For a self-service bot designed to report fraud, you might define a tool named CONFIRM\$1SUBMISSION to collect specific information from the customer:

```
- name: CONFIRM_SUBMISSION
  description: Confirm all collected information and finalize the report submission.
  input_schema:
type: object
properties:
  message:
    type: string
    description: A message reviewing all of the collected information and asking 
      for final confirmation before submission.
  report_details:
    type: string
    description: The user's report or complaint details
  reporter_info:
    type: string
    description: Reporter's contact information (if provided) or "Anonymous"
  subject_info:
    type: string
    description: Information about the individual or business being reported
required:
  - message
  - report_details
  - reporter_info
  - subject_info
```

However, you can use the FOLLOW\$1UP\$1QUESTION tool instead to collect this information step-by-step, as shown in the following sample:

```
- name: FOLLOW_UP_QUESTION
  description: Ask follow-up questions to understand customer needs and collect additional 
information throughout the complaint process. Use this for all information gathering 
steps including confidentiality preferences, contact info, subject details etc.
  input_schema:
type: object
properties:
  message:
    type: string
    description: The message you want to send next in the conversation with the 
      customer. This message should be grounded in the conversation and polite. 
      Use this for asking clarification questions, collecting contact information, 
      gathering subject details, and all other follow-up steps in the complaint 
      process.
required:
  - message
```

### Prompt instructions
<a name="follow-up-question-prompt-instructions"></a>

Add instructions to your prompt to guide your self-service bot on when to use the FOLLOW\$1UP\$1QUESTION tool. For example:

```
CRITICAL: Use FOLLOW_UP_QUESTION for all information gathering steps after the initial analysis. 
Do NOT proceed to other tools until you have collected all required information. Use this tool 
to disambiguate customer intent when unclear.

When using FOLLOW_UP_QUESTION:
1. Ask one specific question at a time
2. Focus on collecting required information for the most likely intent
3. Be conversational but direct
4. Acknowledge information the customer has already provided
5. Only move to other tools (like CONFIRM_SUBMISSION or TRIP_BOOKING) when you have all required 
   information
```

### Example conversations
<a name="follow-up-question-example-conversations"></a>

Following are three example conversations that show the FOLLOW\$1UP\$1QUESTION tool in use. 
+ Example 1: When a customer asks about reporting fraud, the model needs to collect information (such as `report_details`, `reporter_info`, `subject_info`) from the customer to create a report. Instead of using a custom tool named CONFIRM\$1SUBMISSION tool to collect the information, this example shows how it can start collecting required information using the FOLLOW\$1UP\$1QUESTION tool. 
+ Example 2: This example continues the same theme, showcasing the alternate information that can be retrieved for reporter's contact information by using the FOLLOW\$1UP\$1QUESTION tool.
+ Example 3: This example indicates how the model should respond to vague requests from customer and clarify things by using the FOLLOW\$1UP\$1QUESTION tool.

```
<examples>
<example>
    <conversation>
        [CUSTOMER] I want to report someone who I think is committing fraud
    </conversation>
    <thinking>
        The customer wants to report fraud. I need to collect specific information 
        including details about the suspected fraud, reporter information, and 
        subject information. I'll start by asking about the suspected fraudulent activity.
    </thinking>
    <tool>
        [FOLLOW_UP_QUESTION(message="I'd be happy to help you report suspected fraud. 
        Could you please describe the fraudulent activity you've observed?")]
    </tool>
</example>

<example>
    <conversation>
        [AGENT] Can you provide me your full address?
        [CUSTOMER] I don't feel comfortable sharing my address
    </conversation>
    <thinking>
        The caller declined to share their address. I should respect their privacy 
        concerns while still trying to collect alternative contact information.
    </thinking>
    <tool>
        [FOLLOW_UP_QUESTION(message="I understand your privacy concerns. That's 
        completely fine. Would you be comfortable providing a phone number or email 
        address instead? Or you can choose to remain anonymous.")]
    </tool>
</example>

<example>
    <conversation>
        [CUSTOMER] I'm not getting my benefit payments anymore
    </conversation>
    <thinking>
        The customer is reporting a payment issue. This sounds like a general service 
        issue rather than fraud. I should clarify if they need assistance with their benefits.
    </thinking>
    <tool>
        [FOLLOW_UP_QUESTION(message="I'm sorry to hear about the issue with your payments. 
        To help me understand better, could you tell me when you last received a payment 
        and if you've received any notification about why they stopped?")]
    </tool>
</example>
</examples>
```