AWS quick documentation change
Summary
Restructured documentation to focus on step types, @ references, and flow organization. Removed sections about reasoning groups and user inputs while adding detailed explanations of step categories (AI responses, flow logic, data insights, actions, user input). Simplified mode descriptions and reorganized content hierarchy.
Security assessment
The changes focus on improving conceptual documentation and terminology organization rather than addressing security vulnerabilities. While action steps involving third-party integrations previously mentioned data security implications, this version removes those specific security considerations. No new security advisories, vulnerability fixes, or explicit security feature documentation were added.
Diff
diff --git a/quick/latest/userguide/terminology-and-key-concepts.md b/quick/latest/userguide/terminology-and-key-concepts.md index 63458bfc7..a15c10ff0 100644 --- a//quick/latest/userguide/terminology-and-key-concepts.md +++ b//quick/latest/userguide/terminology-and-key-concepts.md @@ -5 +5 @@ -User inputsAI-generated responsesAction stepsReasoning groupsEditor and Run modeGetting started with terminology +Steps and @ referencesEditor and Run mode @@ -9 +9 @@ User inputsAI-generated responsesAction stepsReasoning groupsEditor and Run mode -Amazon Quick Flows empowers business users to transform their everyday tasks into workflows for individual and team productivity. Understanding the core terminology and concepts helps you effectively create, run, share, and maintain Flows within your organization. Flows offer agentic runtime support enabling end users to chat with their workflow and request updates like summarizing an output or skipping a step. +Understanding the core terminology and concepts helps you effectively create, run, share, and maintain flows within your organization. @@ -11 +11 @@ Amazon Quick Flows empowers business users to transform their everyday tasks int -## User inputs +## Steps and @ references @@ -13 +13 @@ Amazon Quick Flows empowers business users to transform their everyday tasks int -User inputs represent the entry points where users provide information to initiate a flow. These steps capture the necessary context from a user that is needed to execute the flow. Input steps can include text fields for user queries or file upload capabilities for document processing. The design of input steps directly impacts user experience and determines how effectively users can communicate their needs to the flow. +A flow is made up of steps that each perform a specific function, such as calling an action, querying your data, or searching the web. Most steps are controlled through a natural language prompt. @@ -15 +15 @@ User inputs represent the entry points where users provide information to initia -When configuring user inputs, consider the type of information your flow needs to process and choose appropriate input methods that align with user expectations. Well-designed user inputs provide clear guidance about what information is required through placeholder text and some default values, if applicable. +Steps pass data to each other using @ references. When you write a prompt inside a step, type @ to see a menu of previous steps. Select one to include that step's output as context in your prompt. For example, if Step 1 collects a customer's issue and Step 3 needs to classify it, Step 3's prompt might say: "Classify the issue in @Customer Issue by severity (low, medium, high)." @@ -17 +17 @@ When configuring user inputs, consider the type of information your flow needs t -###### Note +The available step types are organized into the following groups: @@ -19 +19 @@ When configuring user inputs, consider the type of information your flow needs t -Eligible steps can be referenced in subsequent steps through the @ reference notation. Type @ in prompt to see menu of eligible steps within that flow. +AI responses @@ -21 +20,0 @@ Eligible steps can be referenced in subsequent steps through the @ reference not -## AI-generated responses @@ -23 +22 @@ Eligible steps can be referenced in subsequent steps through the @ reference not -AI-generated responses are outputs that define how Amazon Quick Flows presents results and information back to users. These steps encompass various formats including text responses, AI-generated images using Bedrock models, or structured data presentations as Amazon Quick Sight visuals. Adding a specific step for AI-generated response denotes what data will be used to produce output for that step, which will be available later in the flow for further processing. These outputs can be generated from connected knowledge bases, Amazon Quick Sight dashboards and topics, spaces defined in Quick, or results from the web. + * **Chat agent** — Gets a response from a custom agent and can take actions in connected applications. @@ -25 +24 @@ AI-generated responses are outputs that define how Amazon Quick Flows presents r -Image generation capabilities allow Flows to create visual content dynamically, creating customized, consistent images for ads, marketing assets, stock photos, social media, and e-commerce content. These AI-powered image outputs can be tailored to specific requirements and integrated seamlessly with other output formats within the same Flow. + * **Research** — Invokes Amazon Quick Research to generate research reports as part of your workflow. @@ -27 +26 @@ Image generation capabilities allow Flows to create visual content dynamically, -## Action steps + * **Web Search** — Generates responses using internet search results. @@ -29 +28 @@ Image generation capabilities allow Flows to create visual content dynamically, -Action steps enable Amazon Quick Flows to interact with external systems and perform automated tasks beyond content generation. These steps connect your flows to third-party applications, AWS services, and internal systems through a comprehensive library of pre-built connectors. Action steps can perform tasks such as sending notifications, updating databases, creating calendar events, or any custom action defined with MCP or an OpenAPI specification (learn more about Quick actions in [Action steps in flows](./action-steps-in-flows.html)). + * **General knowledge** — Gets a response directly from Amazon Bedrock models, with configurable response preferences for speed or versatility. @@ -31 +30 @@ Action steps enable Amazon Quick Flows to interact with external systems and per -The extensive action connector library supports integration with popular business applications, development tools, and AWS services. When implementing action steps, consider authentication requirements, data security implications, and the specific permissions needed for your intended integrations. + * **UI Agent** — Navigates public websites that do not require a login and performs tasks like scrolling to find information or filling forms. @@ -33 +32 @@ The extensive action connector library supports integration with popular busines -## Reasoning groups + * **Create Image** — Generates AI images from text inputs. @@ -35 +33,0 @@ The extensive action connector library supports integration with popular busines -Reasoning groups organize related processing logic within Amazon Quick Flows, allowing creators to control how the flow executes, using natural language instructions. These groups help manage the flow of information and decision-making processes by grouping related steps that work together to accomplish specific objectives. Reasoning groups improve workflow organization, making Flows easier to understand, maintain, and troubleshoot. @@ -37 +34,0 @@ Reasoning groups organize related processing logic within Amazon Quick Flows, al -Within reasoning groups, you can establish dependencies between steps, control execution order, and manage data flow between different components of your workflow. This organizational structure becomes particularly valuable when building flows that require multiple processing stages or conditional logic. Instructions within reasoning groups provide specific guidance to define how the flow should interpret inputs, process information, and generate appropriate responses. @@ -39 +35,0 @@ Within reasoning groups, you can establish dependencies between steps, control e -## Editor and Run mode @@ -41 +37,17 @@ Within reasoning groups, you can establish dependencies between steps, control e -Amazon Quick Flows provides two distinct modes for working with flows: Editor mode for building and configuring flows, and Run mode for executing and testing them. You can switch between these modes using the mode toggle in the interface. +Flow logic + + + * **Reasoning Group** — Groups related steps together with natural language instructions that define conditions, loops, validation, and execution order. + + + + +Data insights + + + * **Quick data** — Retrieves responses from spaces and knowledge bases. + + * **Dashboards and topics** — Gets insights from Amazon Quick Sight dashboards and topics. + + + @@ -43 +55 @@ Amazon Quick Flows provides two distinct modes for working with flows: Editor mo -In Editor mode, you design your flow by adding and configuring steps, defining logic, and setting up the workflow structure. This is where you build the automation before making it available to users. +Actions @@ -45 +56,0 @@ In Editor mode, you design your flow by adding and configuring steps, defining l -Run mode allows you to execute and test your flow. Within Run mode, you can interact with your flow using two different interaction patterns: chat mode for conversational, iterative interactions where users can ask follow-up questions and refine their requests, or structured mode for guided, step-by-step workflows that follow predetermined paths and ensure consistent data collection. @@ -47 +58,16 @@ Run mode allows you to execute and test your flow. Within Run mode, you can inte -## Getting started with terminology + * **Application actions** — Performs read or write operations in connected third-party applications through pre-built connectors. + + + + +User input + + + * **Text** — Collects free-form text input from users. + + * **Files** — Accepts file uploads from users for document processing. + + + + +## Editor and Run mode @@ -49 +75 @@ Run mode allows you to execute and test your flow. Within Run mode, you can inte -Understanding these core concepts provides the foundation for effectively using Amazon Quick Flows. As you begin building flows, refer back to these definitions to ensure you're leveraging the appropriate components for your specific use cases and organizational requirements. +Editor mode is where you build your flow. You see all the steps laid out and can select each one to change its configuration. Run mode is where you test and execute your flow, with a chat panel where you can ask follow-up questions or refine the output. @@ -57 +83 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -User personas +Components and features @@ -59 +85 @@ User personas -Prerequisites +AI responses