UX Patterns Guide
UI + UX AI And Automation UX emerging

Prompt box

Provide a prompt box that makes the editable draft, included context, source and tool scope, submission behavior, safety limits, blocked states, and recovery paths visible before the request is sent.

Open in lab Compare alternatives
Decision first

Choose this pattern when the problem matches

Use when

  • Users must write or revise an AI request before generation, analysis, transformation, or automation begins.
  • The system can make context, sources, tools, permissions, limits, and submit behavior visible before request execution.
  • The prompt draft and submitted prompt need a recoverable lifecycle separate from AI output.

Avoid when

  • The task is better expressed as a fixed form, button, or command with known parameters.
  • Users only need query suggestions or retrieval search, not AI generation or transformation.
  • The product cannot disclose or constrain what context the model will use.
  • High-risk automation requires structured review, approval, or form fields before any natural-language request runs.
  • The interface cannot preserve drafts through common failure and navigation states.

Problem it prevents

AI features often invite open-ended requests, but a vague or under-instrumented prompt field hides what context, sources, tools, permissions, limits, and side effects will be included, causing accidental sends, weak outputs, privacy mistakes, and confusion with search or command execution.

Test the behavior

Open the interactive example when you need it

The full lab is intentionally loaded on request. That keeps this reading page fast while preserving the strong and weak states, keyboard checks, and failure scenarios.

In the lab you can
  • switch between strong UI, weak UI, strong UX, and weak UX;
  • trigger required, empty, loading, error, and recovery states;
  • inspect keyboard and accessibility expectations beside the demo.
Launch Prompt box in the lab
Pattern anatomy

What a strong implementation has to make clear

User need

Users may be asking for generation, summarization, extraction, classification, rewrite, planning, data analysis, tool use, or workflow automation.

Pattern promise

Provide a prompt box that makes the editable draft, included context, source and tool scope, submission behavior, safety limits, blocked states, and recovery paths visible before the request is sent.

Required state

Empty prompt state with label, helpful instruction, and no implied hidden submission.

Recovery path

Empty-field hint text is treated like a prompt.

Access contract

Provide a programmatic label for the prompt editor and named controls for send, attach, remove context, clear, retry, and cancel.

Quality bar

The difference between expert and weak execution

Strong implementation

Specific, visible, recoverable

  • An assistant composer labels the selected source as Contract draft, shows Attach file, Use selected text, Format: table, and Send, and blocks sending when the referenced file is no longer available.
  • A prompt box expands for a multi-line request, shows Shift+Enter for newline, Enter to send only when configured, and keeps the draft after a failed model request.
  • A user selects a policy paragraph, writes Summarize risks for a non-lawyer, sees Selected text and Output: bullets chips, submits, then edits and resends the exact prompt after the first answer is too broad.
  • A user attaches a spreadsheet, sees that the model can use only the visible sheet, changes the prompt to ask for a CSV-ready summary, and keeps their draft when upload validation fails.
Weak implementation

Vague, hidden, hard to recover from

  • A blank AI field shows only Ask me anything and sends vague requests with hidden page context.
  • A prompt input has attachment and tool icons but no labels, no context summary, and no indication that generated output will need review.
  • A user presses Enter expecting a new line and accidentally sends an unfinished prompt to an external model.
  • A user asks the prompt box to update records, but the surface hides that tool access is disabled until after generation fails.
UI guidance
  • Render the prompt box as a labelled, editable composer with visible draft area, send control, context chips, attachment controls, model or mode indicator when relevant, character or token boundary feedback, and clear disabled or blocked-send reasons.
  • Show exactly what the prompt will include before submission: typed instruction, selected text, attached files, page context, workspace sources, tool access, output format, safety or privacy limits, and whether Enter sends or inserts a newline.
UX guidance
  • Use a prompt box when users need to author a natural-language request for AI generation, transformation, analysis, or automation and must remain in control of the exact request being submitted.
  • Protect users from accidental or misleading submissions by preserving drafts, requiring explicit send for consequential work, validating unavailable context, supporting edit-and-resend, and distinguishing prompt composition from search, command execution, and normal text entry.
Implementation contract

What the implementation must handle

States

  • Empty prompt state with label, helpful instruction, and no implied hidden submission.
  • Typing state with expandable multi-line draft, send affordance, newline behavior, and character or token boundary feedback.
  • Context-attached state with selected text, current page, file, source, or tool chips.
  • Unavailable-context, unsupported-file, over-limit, permission-limited, blocked-safety, and offline states with repair paths.

Interaction

  • The prompt box always exposes the user's editable draft before submission.
  • Send uses the visible draft and the visible context chips; hidden context must be disclosed elsewhere in the same surface.
  • Placeholder, suggestion, or hint text never submits as a user prompt unless the user explicitly selects or types it.
  • Enter, Shift+Enter, Command+Enter, mobile send, and IME composition behavior are stated or follow platform expectations without accidental sends.

Accessibility

  • Provide a programmatic label for the prompt editor and named controls for send, attach, remove context, clear, retry, and cancel.
  • Expose draft, empty-field hint, context chips, over-limit text, blocked send, generation pending, and failed-send states in text.
  • Do not rely on icon-only controls for attach, send, model mode, source, or tool access.
  • Keep focus in or near the prompt box after blocked send, failed upload, validation error, retry, or cancel generation.

Review

  • Can users see the exact request, context, attachments, sources, tools, and output expectation before send?
  • What prevents accidental send from Enter, starter prompts, paste, mobile keyboard actions, or empty-field hint text?
  • Which failures preserve the draft, and which provide repair before submission?
  • Does this surface need a chat interface, prompt suggestions, command palette, search box, or ordinary textarea instead?
Evidence trail

Source-backed claims behind this guidance

Prompt assistant

Microsoft Learn - checked

Supports prompt draft review, edit, keep, and test behavior.

Full agent/debug reference

Problem Context

  • Users may be asking for generation, summarization, extraction, classification, rewrite, planning, data analysis, tool use, or workflow automation.
  • A prompt may include typed text, selected page content, files, current object metadata, conversation history, workspace knowledge, external tools, hidden system instructions, or no additional context.
  • The AI response can be non-deterministic, incomplete, ungrounded, delayed, blocked, rate-limited, or require user review before use.
  • Prompt input often sits near prompt suggestions, generated responses, chat history, citations, approvals, attachments, and model-selection controls.
  • Mobile keyboards, IME composition, speech input, paste, file upload, and Enter/newline behavior can change how users submit or edit prompts.

Selection Rules

  • Choose prompt box when the central user action is composing and submitting an AI request.
  • Use prompt suggestions when the interface provides starter requests that should load into an editable prompt box before send.
  • Use command palette when the typed input selects known app commands or routes rather than open-ended AI output.
  • Use search suggestions when the input creates or refines a retrieval query and returns matching items.
  • Use textarea when the field is ordinary human-authored long text without AI context, sources, model state, or generated-output lifecycle.
  • Use chat interface when conversation history, assistant turns, follow-up prompts, streaming responses, and multi-turn memory are the primary surface.
  • Require explicit send when a prompt can trigger tool use, publish content, contact people, alter records, reveal sensitive data, or spend money.
  • Show context inclusion and repair paths before send when selected text, files, workspace sources, or tools are unavailable, stale, too large, or permission-limited.
  • Keep empty-field hint copy instructional but never treat hint text as submitted prompt content.
  • Preserve draft text, attachments, selected context, focus, and scroll when send fails, model availability changes, or users navigate back from output review.

Required States

  • Empty prompt state with label, helpful instruction, and no implied hidden submission.
  • Typing state with expandable multi-line draft, send affordance, newline behavior, and character or token boundary feedback.
  • Context-attached state with selected text, current page, file, source, or tool chips.
  • Unavailable-context, unsupported-file, over-limit, permission-limited, blocked-safety, and offline states with repair paths.
  • Submitted prompt state that records the exact prompt sent and distinguishes it from the editable draft.
  • Generation pending, failed request, rate limited, retry, edit-and-resend, cancel, and cleared draft states.
  • Sensitive-content warning, external-model disclosure, tool-use review, and human-approval handoff states when relevant.
  • Mobile keyboard state with accessible send, attachment, newline, voice input, and draft-preservation behavior.

Interaction Contract

  • The prompt box always exposes the user's editable draft before submission.
  • Send uses the visible draft and the visible context chips; hidden context must be disclosed elsewhere in the same surface.
  • Placeholder, suggestion, or hint text never submits as a user prompt unless the user explicitly selects or types it.
  • Enter, Shift+Enter, Command+Enter, mobile send, and IME composition behavior are stated or follow platform expectations without accidental sends.
  • Context chips can be inspected, removed, repaired, or replaced before the request is sent.
  • Blocked send states explain whether the problem is empty prompt, missing context, unsupported file, safety policy, permission, rate limit, model availability, or network state.
  • After failed send or blocked send, the draft and attachments remain available and focus stays near the repair control.
  • After submit, users can inspect the exact prompt, edit and resend it, or clear the draft without losing the previous output.

Implementation Checklist

  • Define prompt payload structure: user text, selected content, files, source IDs, tool permissions, conversation scope, output format, model or mode, and safety flags.
  • Keep prompt draft state separate from submitted prompt history, generated answer, command execution state, and search query state.
  • Implement labelled controls for send, attach, context source, remove context, clear draft, edit previous prompt, retry, cancel generation, and open safety or privacy details.
  • Validate empty prompt, over-limit text, unsupported attachments, unavailable sources, revoked permissions, offline state, rate limits, and blocked content before send.
  • Preserve drafts across focus loss, route changes within the task, failed requests, file validation errors, and model availability changes.
  • Test keyboard, screen reader, mobile keyboard, paste, IME composition, dictation, long prompts, file attachments, sensitive content, and low-connectivity states.

Common Generated-UI Mistakes

  • Showing Ask anything as the only instruction while hiding what sources and tools the model can use.
  • Auto-sending prompt suggestions, pasted content, or empty-field hint wording.
  • Using a prompt box for deterministic commands that should be explicit buttons or command-palette actions.
  • Styling a prompt box like search and implying generated answers are exact retrieved results.
  • Letting users attach files or select context without showing whether the model can read them.
  • Clearing the draft after a rate limit, upload failure, safety block, or network error.
  • Hiding consequential tool use behind conversational phrasing.

Critique Questions

  • Can users see the exact request, context, attachments, sources, tools, and output expectation before send?
  • What prevents accidental send from Enter, starter prompts, paste, mobile keyboard actions, or empty-field hint text?
  • Which failures preserve the draft, and which provide repair before submission?
  • Does this surface need a chat interface, prompt suggestions, command palette, search box, or ordinary textarea instead?
  • Are privacy, sensitive-data, external-model, and tool-use consequences visible at the prompt box boundary?
  • Can users edit and resend the exact prompt after reviewing a weak, failed, or incomplete output?
Accessibility
  • Provide a programmatic label for the prompt editor and named controls for send, attach, remove context, clear, retry, and cancel.
  • Expose draft, empty-field hint, context chips, over-limit text, blocked send, generation pending, and failed-send states in text.
  • Do not rely on icon-only controls for attach, send, model mode, source, or tool access.
  • Keep focus in or near the prompt box after blocked send, failed upload, validation error, retry, or cancel generation.
  • Announce status messages without moving focus when context is added, removed, blocked, submitted, or restored.
  • Respect IME composition, dictation, mobile keyboards, zoom, long text, screen readers, and reduced motion during generation state changes.
Keyboard Behavior
  • Tab reaches prompt editor, context chips, attach, mode, send, clear, and related controls in a predictable order.
  • Enter behavior is explicit: either send on Enter with Shift+Enter for newline, or newline on Enter with a separate send shortcut.
  • Escape closes attachment menus, source pickers, and suggestion popovers without deleting the prompt draft.
  • Backspace or Delete removes a focused context chip only after focus is clearly on that chip.
  • Command+Enter or Control+Enter may send from a multi-line prompt when the shortcut is exposed.
  • After send, focus moves to the generated-output status or remains in the prompt box according to the product's stated flow.
Variants
  • Single-turn prompt box
  • Expandable prompt composer
  • Prompt box with context chips
  • Prompt box with file attachments
  • Prompt box with output format controls
  • Prompt box with tool-use review
  • Inline prompt box
  • Floating assistant input
  • Voice-assisted prompt box
  • Mobile prompt composer

Verification

Source trail checked:

Saved items