AWS connect documentation change
Summary
Restructured documentation with expanded configuration guidance, added FOLLOW_UP_QUESTION tool details, and improved setup instructions for Amazon Q self-service
Security assessment
Changes focus on feature capabilities and configuration workflows without addressing vulnerabilities or security controls. The fraud reporting example demonstrates privacy-aware data collection patterns but doesn't introduce security-specific features
Diff
diff --git a/connect/latest/adminguide/generative-ai-powered-self-service-q.md b/connect/latest/adminguide/generative-ai-powered-self-service-q.md index e507fd180..6c1617513 100644 --- a//connect/latest/adminguide/generative-ai-powered-self-service-q.md +++ b//connect/latest/adminguide/generative-ai-powered-self-service-q.md @@ -5 +5 @@ -Default system actions for Amazon Q in Connect self-serviceCustom actions for Amazon Q in Connect self-service +Default system toolsSet up self-serviceCustom actions for self-serviceFOLLOW_UP_QUESTION tool @@ -9 +9 @@ Default system actions for Amazon Q in Connect self-serviceCustom actions for Am -Amazon Q in Connect supports customer self-service use cases in chat and IVR. It can handle Q&A support, recommend actions to customers through step-by-step guides, and complete actions on behalf of customers. For example, it can reschedule appointments and book trips. +###### Tip @@ -11 +11 @@ Amazon Q in Connect supports customer self-service use cases in chat and IVR. It -If a customer requires additional support, Amazon Q in Connect provides a seamless transition to your agents. It preserves the full context of the conversation, which ensures a cohesive customer experience. +Check out this course from AWS Workshop: [Customizing Amazon Q in Connect Self-Service](https://catalog.workshops.aws/amazon-q-in-connect/en-US/customizing-amazon-q-in-connect-self-service). @@ -13 +13 @@ If a customer requires additional support, Amazon Q in Connect provides a seamle -You can configure Amazon Q in Connect use cases for self-service by using the same customization capabilities you use for agent assistance use cases. For more information about how to customize Amazon Q in Connect, see [Customize Amazon Q in Connect](./customize-q.html). +Amazon Q in Connect supports customer self-service use cases in chat and voice (IVR) channels. It can: @@ -15 +15 @@ You can configure Amazon Q in Connect use cases for self-service by using the sa -To enable Amazon Q in Connect for self-service uses cases for both testing and production purposes, you need to enable Amazon Q in Connect in an Amazon Connect bot. After Amazon Q in Connect is associated with a Amazon Connect bot, you can use the [Get customer input](./get-customer-input.html) flow block in a flow to designate when Amazon Q in Connect should start handling a customer interaction and for which types of customer interactions. + * Answer customer questions. @@ -17 +17 @@ To enable Amazon Q in Connect for self-service uses cases for both testing and p -When adding Amazon Q in Connect to a flow, it is important to use a [Check contact attributes](./check-contact-attributes.html) flow block to determine what should happen after Amazon Q in Connect has completed its turn of the conversation. Amazon Q in Connect will save the selected **Tool** name as a Lex session attribute, which can then be accessed by using the **Check contact attributes** block. + * Provide step-by-step guidance. @@ -19 +19 @@ When adding Amazon Q in Connect to a flow, it is important to use a [Check conta -The following image shows an example **Check contact attributes** properties page. The **Session Attribute Key** is set to **Tool.** + * Complete actions like rescheduling appointments and booking trips. @@ -21 +20,0 @@ The following image shows an example **Check contact attributes** properties pag - @@ -23 +21,0 @@ The following image shows an example **Check contact attributes** properties pag -By using the **Check contact attributes** flow block, you can set conditional logic on the default Amazon Q in Connect tools **Escalation** and **Complete** , as well any custom tools you define. The following image shows an example of how you can make a routing decision based on whether Amazon Q in Connect decides a contact has been successfully completed in self-service, or if the contact should be escalated to a contact center agent. @@ -25 +22,0 @@ By using the **Check contact attributes** flow block, you can set conditional lo - @@ -27 +24 @@ By using the **Check contact attributes** flow block, you can set conditional lo -## Default system actions for Amazon Q in Connect self-service +When customers need additional help, Amazon Q in Connect seamlessly transfers them to agents while preserving the context of the full conversation. @@ -29 +26 @@ By using the **Check contact attributes** flow block, you can set conditional lo -When interacting with a customer, Amazon Q in Connect has four default actions to select from. These actions, called **Tools** in the AI prompt, work out-of-the-box and can be modified further with customizations. +###### Contents @@ -31 +28 @@ When interacting with a customer, Amazon Q in Connect has four default actions t - 1. **QUESTION** : Amazon Q in Connect will provide answers to direct questions and seek relevant information if no other tool can directly solve the customer query. + * Default system tools @@ -33 +30 @@ When interacting with a customer, Amazon Q in Connect has four default actions t - 2. **ESCALATION** : Amazon Q in Connect will automatically escalate to a contact center agent if a customer seeks help from a contact center agent. + * Set up self-service @@ -35 +32 @@ When interacting with a customer, Amazon Q in Connect has four default actions t - 3. **CONVERSATION** : Amazon Q in Connect will engage in simple dialogue, if there is no specific customer intent. + * Custom actions for self-service @@ -37 +34 @@ When interacting with a customer, Amazon Q in Connect has four default actions t - 4. **COMPLETE** : Amazon Q in Connect will wrap up the conversation if the customer no longer has anything else they need help with. + * FOLLOW_UP_QUESTION tool @@ -42 +39 @@ When interacting with a customer, Amazon Q in Connect has four default actions t -## Custom actions for Amazon Q in Connect self-service +## Default system tools @@ -44 +41 @@ When interacting with a customer, Amazon Q in Connect has four default actions t -You can also add custom tools for Amazon Q in Connect to select from, such as surfacing next best actions for the end-customer to take or delegating to a pre-existing Lex bot you have created. You can define these custom tools by customizing your AI prompts. Below are two examples of possible custom tools you can add to your Amazon Q in Connect configurations. +Amazon Q in Connect comes with the following built-in tools that work out-of-the-box: @@ -46 +43 @@ You can also add custom tools for Amazon Q in Connect to select from, such as su -When adding custom **Tool** definitions to an AI prompt, we encourage you to also add relevant examples to the AI prompt to help Amazon Q in Connect's reasoning to select these actions when appropriate. + 1. **QUESTION** : Provides answers and gathers relevant information when no other tool can directly address the query. @@ -48 +45 @@ When adding custom **Tool** definitions to an AI prompt, we encourage you to als -After you have added a custom **Tool** to your AI prompt, you can create branching logic for each selected **Tool** using the **Get contact attributes** flow block as described above. Amazon Q in Connect will save the selected Tool name as a Lex session attribute which can then be accessed by using the **Check contact attribute** block. + 2. **ESCALATION** : Automatically transfers to an agent when customers request human assistance. @@ -50 +47 @@ After you have added a custom **Tool** to your AI prompt, you can create branchi -### Disambiguate the customer intent +###### Note @@ -52 +49 @@ After you have added a custom **Tool** to your AI prompt, you can create branchi -A simple yet effective generative AI assistant is one which can chat with customers and gather information prior to sending a contact to an agent. In this use case, you can use Amazon Q in Connect without a knowledge base and instead use a simple set of instructions to collect information, summarize it, and present it to an agent, by using a step-by-step guide. For more information, see [Display contact context in the agent workspace when a contact begins in Amazon Connect](./display-contact-attributes-sg.html). +When ESCALATION is selected, it takes the **Error** branch of the **Get customer input** block. @@ -54 +51,92 @@ A simple yet effective generative AI assistant is one which can chat with custom -**Example Tool definition for a disambiguation use case**. You can remove all default tools except **Conversation** and add one new custom tool called **Handoff** : + 3. **CONVERSATION** : Engages in basic dialogue when there's no specific customer intent. + + 4. **COMPLETE** : Concludes the interaction when customer needs are met. + + 5. **FOLLOW_UP_QUESTION** : Enables more interactive and information-gathering conversations with customers. For more information about using this tool, see FOLLOW_UP_QUESTION tool. + + + + +You can customize these default tools to meet your specific requirements. + +## Set up self-service + +Follow these steps to enable Amazon Q in Connect for self-service: + + 1. Enable Amazon Q in Connect 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 Amazon Q in Connect intent](./create-qic-intent-connect.html). + + 2. Add an [Amazon Q in Connect](./q-block.html) block to your flow. + + 3. Add a [Get customer input](./get-customer-input.html) block to your flow to specify: + + * When Amazon Q in Connect 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.html). + + 4. (Optional) Add a [Check contact attributes](./check-contact-attributes.html) block to your flow and configure it to determine what should happen after Amazon Q in Connect 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** = the name of the tool + +Amazon Q in Connect saves the selected tool name as a Lex session attribute. This session attribute can then be accessed by using the **Check contact attributes** block. + + 5. (Optional) Define routing logic based on the tool selected by Amazon Q in Connect: + + * Route COMPLETE responses to end the interaction. + + * Route custom tool responses (like TRIP_BOOKING) to specific workflows. + +The following image shows an example of how you can make a routing decision based on what Amazon Q in Connect decides. + + + + + + +## Custom actions for self-service + +You can extend Amazon Q in Connect'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 Amazon Q in Connect select appropriate actions. + + * Use the [Check contact attributes](./check-contact-attributes.html) 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_BOOKING is specified. + + + + + + +### Example: Disambiguate the customer intent + +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.html). + + + + +Following is an example tool definition for disambiguation. You can remove all default tools except CONVERSATION and add one new custom tool called HANDOFF: @@ -83,3 +171 @@ A simple yet effective generative AI assistant is one which can chat with custom -### Recommend an action for a customer - -You can configure next best actions in Amazon Connect by using Amazon Connect flows. You can configure automated actions and create Amazon Connect 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.html). Amazon Q in Connect saves the selected **Tool** name as a Lex session attribute. The attribute can then be accessed by using the **Check contact attributes** flow block. +### Example: Recommend an action for a customer @@ -87 +173 @@ You can configure next best actions in Amazon Connect by using Amazon Connect fl -When using the **Check contact attributes** flow block to determine which **Tool** Amazon Q in Connect 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 create a **Trip Booking** tool and then in your flows, match this return value in the **Check contact attributes** block to a step-by-step guide that can be rendered directly in the customer's chat interface. For more information see [Deploy step-by-step guides in Amazon Connect chats](./step-by-step-guides-chat.html). +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.html). Amazon Q in Connect saves the selected tool name as a Lex session attribute. The attribute can then be accessed by using the **Check contact attributes** flow block. @@ -89 +175 @@ When using the **Check contact attributes** flow block to determine which **Tool -**Example Tool definition for Amazon Q in Connect to recommend (or take) an action:** +Here's an example tool definition for booking a trip: @@ -102,0 +189,178 @@ When using the **Check contact attributes** flow block to determine which **Tool +When using the **Check contact attributes** flow block to determine which tool Amazon Q in Connect 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_BOOKING 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.html). + +## FOLLOW_UP_QUESTION tool + +The FOLLOW_UP_QUESTION tool enhances Amazon Q in Connect 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_UP_QUESTION 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: