Prompt suggestions

A React component in Beamline's AI & agents category.

Ready-made prompts a person can start from or follow up with: chips, cards or a list; a picked one lifts off and flies into the composer as its text, while follow-ups that are still being written hold their place and arrive one after another.

Use it for

  • The empty state of an agent conversation: three to six things the agent is good at, so the first message is one click away.
  • Follow-up questions under an answer, generated while or after it streams.
  • Quick replies in a voice or support agent.

Not for

Anatomy

  • root: a size container with an optional heading and an optional More ideas button
  • suggestion: a button with an optional icon, the label and, in cards and the list, a detail line
  • chips: a row of pills that wraps; cards: a grid of tiles, two across from 24rem and four across from 48rem when there are four; list: full-width rows with an arrow at the end (follow-ups)
  • placeholders while follow-ups are written: the shape of each suggestion with a slow sheen
  • flight: a picture of the picked suggestion that travels into the composer you name (target) and dissolves into its text

Variants

  • layout: chips, cards, list
  • size: sm, md

States

  • rest
  • loading (placeholders; announced once as “Writing suggestions”)
  • arriving (each grows in after the one before)
  • picked (the suggestion flies to the target; the others step back while it travels)
  • refreshing (the old set leaves as ghosts, the new set grows in)
  • empty (renders nothing)

Keyboard

  • One tab stop: Tab reaches the set at the last suggestion focused (the first at the start)
  • ← → (and ↑ ↓) move between suggestions, Home and End to the ends; in right-to-left pages ← and → follow the reading direction
  • Enter or Space picks the focused suggestion
  • Tab moves on to More ideas when there is one

Motion

Suggestions that arrive grow in one after another (a short stagger) and never again on the same render. A picked suggestion is acknowledged at once (onPick runs immediately) and a picture of it lifts off, travels on a short arc into the target's text box, shrinks to the text's height and dissolves as it lands; the others step back while it travels. Refreshing lets the old set fade as ghosts where they stood while the new set grows in (useFlip). Pointing at a card or row lifts its arrow; pressing presses. Reduced motion: no flight and no stagger, fades only.

Props

PropTypeDefaultDescription
items (required)PromptSuggestion[]—{ id, label, prompt?, detail?, icon? }. `prompt` is the text that goes to the composer when it differs from the label.
onPick(suggestion: PromptSuggestion) => void—Runs at once on a pick; put the prompt in the composer or send it.
layout"chips" | "cards" | "list"—Default chips.
size"sm" | "md"—Default md.
headingReactNode—A short line above the set (“Try asking”, “Follow up”); it names the group.
labelstring—The group's accessible name when there is no heading. Default “Suggestions”.
loadingboolean | number—Placeholders while suggestions are written; a number sets how many.
targetRefObject<HTMLElement | null> | (() => HTMLElement | null)—The composer a picked suggestion flies into. Omit for no flight.
onRefresh() => void—Shows More ideas; give a new `items` set in return.
className / classNames / style / refstring / PromptSuggestionsClassNames / CSSProperties / native Ref—

Built from

  • button
  • skeleton

Dependencies

lucide-react

Import

import { PromptSuggestions } from "@/components/prompt-suggestions/prompt-suggestions";

Get it

Prompt suggestions is part of Beamline: 200+ components and 50+ complete screens for React that your coding agent (Claude Code, Codex, Cursor or any MCP client) installs into your app through Beamline's MCP server, as a ready-built package or as plain React source you can change. $49 launch price, one payment, no subscription, lifetime updates, one licence for your whole team. Get Beamline · Connect your agent

More in AI & agents

  • Image generation: The frame an AI image is generated into: a field of brand-hued pixels breathes with the progress while the model works, then the image arrives —…
  • Flowchart: A workflow as steps on a dotted canvas: a trigger, conditions that branch into paths side by side, actions and waits, read top to bottom; during a run…
  • Run trace: One agent run as a waterfall: every step (model calls, tools, retrieval, checks, sub-agents) nested under the step that started it, each a bar on a…
  • Answer compare: Two answers to the same prompt side by side, and a person's verdict: A is better, a tie, B is better, or both are bad, with the reasons that decided it…
  • Response: An assistant's answer as streamed markdown in the system's reading type: bursty tokens flow in at an even pace, each new word fades in through a short…
  • Chat thread: People talking to people: messages grouped by person and day, reactions, delivery and read receipts that glide to the newest message read, who is typing…
  • Model picker: Choose the AI model for a request by what it can do and what it costs: a trigger with the model's name opens a searchable list grouped by provider, with…
  • Task rows: Background work an agent is doing, one row per task: status as a glyph and a word, what it produced, how long it has run or took, a progress bar while…
  • Conversation: The scrolling column of a conversation: follows new content while you are at the bottom, stops when you scroll up to read, and offers a way back; shared…
  • Context cards: The knowledge an agent retrieved before it answered: one card per chunk with what it is about, the text it read with the search words marked, how…
  • Plan: An agent's plan: numbered steps with live status, progress, and Approve / Edit / Reject when it needs sign-off; approving shows progress, and a refusal…
  • Approval card: The agent stops and asks before it acts: what it wants to do, exactly what that changes, any choices it needs, and Approve or Reject; both run your…
  • Tool call: One tool call in an agent's run: status, what it did and a short result on one quiet row that opens to the exact input and output; stops for permission…
  • Recommendation card: One suggestion from the agent that the person may take or leave: what it suggests, why, the expected effect and how sure it is (a meter and a word…
  • Citations: Inline numbered citations that preview their source on hover or focus, plus a numbered source list; streamed answers flow in at an even pace with the…
  • Reasoning: The agent's trace, fed by your stream: a shimmering label and the seconds so far while it works, then "Thought for N seconds"; steps that check off…
  • Attachment: A file tile: preview or typed glyph with the type named, name, size, upload progress, error with retry, and a keyboard-reachable remove.
  • Prompt bar: The agent composer: a field that grows, @ to add a source, / for a command, a model picker, files and dictation, and one button that sends with progress…
  • Selection actions: Select a passage and hand it to the agent: a bar over the selection with quick actions, your own instruction and More; while the agent works it says so…
  • Message: One turn in a conversation with an agent: the person's words in a quiet bubble, the agent's answer on the page with its orb mark, trace, tool calls and…