Cloudscape Design System
  • Get started
  • Foundation
  • Components
  • Patterns
  • Demos
  • Gen AI
  • GitHub 
Cloudscape Design System
  • Get started
  • Foundation
  • Components
  • Patterns
  • Demos
  • Gen AI
  • GitHub 
  • About

Gen AI

  • AI tools
    1
  • LLMs.txt files

  • Foundation
    3
  • Visual affordance
  • Colors
  • Iconography

  • Patterns
    19
  • Pattern abstraction
  • Generative AI chat
  • Ingress
  • Generative AI output label
  • Generative AI loading states
  • Progressive steps
  • Follow-up questions
  • User authorized actions
  • Variables
  • Shortcut menus
  • Response regeneration
  • Artifact previews
  • Conversational history
  • Support prompts
  • Thinking
  • Timeline overview
  • In-chat context
  • Agent management
  • In-flow user input

  • Components
    5
  1. Cloudscape Design System
    • Gen AI: Patterns
    • In-flow user input
    1. Cloudscape Design System
    2. Gen AI: Patterns
    3. In-flow user input

    In-flow user input

    Inline interactions that collect structured input or allow users to review and modify agent-generated output within a generative AI chat.

    On this page

    1. Key UX concepts
    2. Common use cases
    3. General guidelines
    4. Writing guidelines
    5. Accessibility guidelines

    About this page

    Published: June 19, 2026

    Did this page help you?

    Your feedback helps us improve our documentation.
    Provide additional feedback

    Key UX concepts

    The right information at the right time

    Only present an interaction when the agent understands the user's intent and needs something specific from the user to proceed. Don't front-load interactions that could be deferred or resolved automatically.

    Explain why input is needed

    Help users understand the value in providing additional information. Highlight how their input enables the agent to generate better output or execute actions correctly, and the expected outcome.

    Match input mechanism to information type

    Display input methods that complement the type of information to be collected. Questions with a finite set of answers, such as selecting resource IDs or timestamps, should use a succinct form. This reduces errors and improves data quality.

    Common use cases

    Agent needs multiple inputs to execute an action

    An inline form collects the required values directly in the conversation. For example, agent is helping create a resource and progressively displays forms inline based on what information is needed. The steps are synchronous; the output of the previous step, determines the next. Forms appear sequentially and may have agent responses between each step. Completed steps show a summarized read only view.

    Generative AI assistant

    JD
    Set up a scheduled Lambda that runs a cleanup job nightly.

    I'll create a Lambda function triggered by an EventBridge schedule rule to run your cleanup job every night. I just need a few configuration details.

    Lambda function setup
    Complete

    Use of this service is subject to the AWS Responsible AI Policy 

    Agent needs input as part of a multi-step process

    Steps are independent and the agent can process them without waiting for previous results. Forms appear as individual collapsible cards within the conversation. Each step resolves on its own and doesn't block subsequent steps, similar to asynchronous creation.

    Generative AI assistant

    JD
    Help me set up a nightly cleanup Lambda function.

    Happy to help. I'll walk you through the setup step by step.

    1. Lambda function setup (1 of 3)
      Complete
      Function name
      nightly-cleanup
      Runtime
      Python 3.12
      Memory
      256 MB
      Timeout
      30 seconds
    2. EventBridge schedule (2 of 3)
      Complete
      Schedule
      Every night at midnight UTC
      Target
      nightly-cleanup
    3. Target resources (3 of 3)

      Which resources should the cleanup function target?

      View available S3 buckets 
    Use of this service is subject to the AWS Responsible AI Policy 

    Editing values inline

    An inline edit within the response allows the user to review and optionally modify the value the agent has created.

    Generative AI assistant

    JD
    I want to build a landing page for my SaaS product. It needs a waitlist signup form and Stripe payment integration for early access.

    I've created an environment for you so we have a place to track everything, code, infrastructure, and deployments.

    Project FreelancerHub

    Now a few quick questions so I can set up the right backend for you:

    Use of this service is subject to the AWS Responsible AI Policy 

    General guidelines

    Do

    • Limit to 5 or fewer input fields per form to keep cognitive load low.
    • When a value in the response is editable inline, display an edit icon button next to it so users can identify it as modifiable.
    • For interaction with a single form, disable inputs and show a success indicator after submission.
    • When possible, pre-fill fields with values inferred from context to reduce user effort.

    Don't

    • Don't use embedded flows to clarify user intent. Inline form input collects values to execute an action. If you need to clarify user intent, use follow-up questions instead.
    • Don't include optional fields. Only ask for what's required to proceed.

    Writing guidelines

    General writing guidelines

    • Use sentence case, but continue to capitalize proper nouns and brand names correctly in context.

    • Use end punctuation, except in headers and buttons. Don’t use exclamation points.

    • Use present-tense verbs and active voice.

    • Don't use please, thank you, ellipsis (...), ampersand (&), e.g., i.e., or etc. in writing.

    • Avoid directional language.

      • For example: use previous not above, use following not below.

    • Use device-independent language.

      • For example: use choose or select not click.

    Component-specific guidelines

    Card title

    • Be specific to the resource or action. Avoid generic labels like Information required or Configuration needed.

    Accessibility guidelines

    General accessibility guidelines

    • Follow the guidelines on alternative text and Accessible Rich Internet Applications (ARIA) regions for each component.

    • Make sure to define ARIA labels aligned with the language context of your application.

    • Don't add unnecessary markup for roles and landmarks. Follow the guidelines for each component.

    • Provide keyboard functionality to all available content in a logical and predictable order. The flow of information should make sense.

    Did this page help you?

    Your feedback helps us improve our documentation.
    Provide additional feedback
    • About
    • Connect
    • Privacy 
    • Site terms 
    • © 2026, Amazon Web Services, Inc. or its affiliates. All rights reserved.
    Made with ❤️ at AWS