Follow-up questions
Ways to request additional information from users to help generate more accurate and relevant responses.
Ways to request additional information from users to help generate more accurate and relevant responses.
Decide whether to gather information before showing output or during the interaction. For high-impact decisions or when confidence is low, collect details first. When multiple questions are needed, collecting them sequentially reduces cognitive load and keeps each decision focused. For other scenarios, start with an initial response and ask follow-up questions to refine results.
Provide clear options for users to proceed, skip, or exit at each step of the interaction. This ensures users feel in control of the experience and reduces friction. When structured options don’t meet the user’s needs, ensure they can always access the prompt input to provide open-ended context in their own words.
Help users access information that isn't readily available. Provide links or instructions on where to find required data when appropriate. This ensures users can provide accurate information even when it's not immediately at hand.
Information type | Input method | Examples |
|---|---|---|
Clarifying user intent | Present sequential predefined choices in a dismissible dialog docked above prompt input. | Context is needed upfront to generate an accurate response. Multiple back-and forth exchanges would otherwise be required. |
Guiding a conversation | Present recommended inputs with support prompt group. | The initial response applies broadly to multiple situations. A follow-up selection narrows it to the user's specific case. There are up to five valid choices. |
When users provide ambiguous or incomplete information, or when a request requires additional information to generate an accurate response, a dismissible dialog collects structured input upfront, reducing back-and-forth exchanges in the thread.
When an initial response applies broadly but a follow-up selection can tailor it to the user's specific situation, a support prompt group presents a constrained set of options after the response.
Both are great options for running containers. Here are the key differences:
AWS Fargate:
ECS on EC2:
To provide a more tailored recommendation, what's your primary concern when choosing a container orchestration solution?
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.
Be specific and action-oriented. Dialog titles should clearly indicate the action being performed or the purpose of the dialog, often by combining an action verb with the resource or concept involved.
For example: Any specific constraints I should know about?
Use placeholder text to provide a brief example or hint of the expected input format, not as a replacement for a label.
Keep placeholder text concise and descriptive enough to guide the user without cluttering the input field.
If the button performs the primary action indicated in the dialog title, the verb used in the button label should match the verb in the title.
Follow the writing guidelines for button.
Limit support prompt labels to less than 72 characters.
Follow writing guidelines for support prompt group
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.