> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tryflowy.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick Actions

> One-click contextual prompts that turn your selection into the next piece of work.

export const VideoPlayer = ({src, poster, aspectRatio = "16 / 9", title, className = ""}) => {
  const [playing, setPlaying] = useState(false);
  if (playing) {
    return <div className={`not-prose relative mx-auto my-6 w-full max-w-screen-md overflow-hidden rounded-2xl border border-gray-950/10 dark:border-white/10 ${className}`} style={{
      aspectRatio
    }}>
        <video src={src} controls autoPlay playsInline className="h-full w-full object-contain" />
      </div>;
  }
  return <button type="button" aria-label={title ? `Play video: ${title}` : "Play video"} style={{
    aspectRatio
  }} className={`not-prose group relative mx-auto my-6 block w-full max-w-screen-md cursor-pointer overflow-hidden rounded-2xl border border-gray-950/10 bg-gray-100 dark:border-white/10 dark:bg-white/5 ${className}`} onClick={() => setPlaying(true)}>
      <img src={poster} alt={title || "Video thumbnail"} className="h-full w-full cursor-pointer object-cover" />
      <div className="absolute inset-x-0 bottom-0 h-20 bg-gradient-to-t from-black/80 to-transparent sm:h-28" />
      <div className="absolute bottom-6 flex w-full items-center justify-between px-6">
        <p className="max-w-sm text-left text-lg font-semibold leading-tight text-white">
          {title}
        </p>
        <div className="rounded-full p-3 shadow-lg transition-all duration-300 group-hover:scale-110 group-active:scale-95" style={{
    backgroundColor: "#5C9987"
  }}>
          <svg width="24" height="24" viewBox="0 0 24 24" fill="#ffffff" aria-hidden="true">
            <path d="M8 5v14l11-7L8 5z" />
          </svg>
        </div>
      </div>
    </button>;
};

Click the Flowy AI dock at the bottom of the [canvas](/canvas/overview) and a row of suggestion chips appears above the composer. These are **quick actions**: ready-made prompts that read what you have selected and propose the most useful next step. Click one and the [Flowy AI](/canvas/ai/overview) chat panel opens with the full prompt staged and your selection attached — tweak it or send it as-is, and the assistant starts building on the canvas.

<VideoPlayer src="/videos/canvas/quick-actions.mp4" poster="/images/posters/canvas/quick-actions.jpg" title="Watch: quick actions turn selections into new work" />

## They follow your selection

The chips change as your context changes. Select an image and you get image moves; select several nodes and you get composition moves; select nothing and they read the board as a whole.

| Context                                        | Quick actions                                                     |
| ---------------------------------------------- | ----------------------------------------------------------------- |
| Empty canvas                                   | **Brand concept** · **Storyboard ad** · **Product video**         |
| One image selected                             | **Animate image** · **Image variants** · **Add storyboard**       |
| One video selected                             | **Improve video** · **Make variants** · **Explain setup**         |
| One storyboard selected                        | **Generate scenes** · **Tighten story** · **Make video plan**     |
| Multiple nodes selected (with images or video) | **Compose video** · **Storyboard these** · **Organize selection** |
| Nothing selected, canvas has storyboards       | **Continue storyboard** · **Find gaps** · **Layout canvas**       |
| Nothing selected, other nodes on canvas        | **Audit canvas** · **Make video** · **Organize flow**             |

A few examples of what they do:

* **Compose video** looks at the selected nodes and builds a video that combines them into one polished shot.
* **Animate image** uses the selected image as the source reference for a cinematic video.
* **Make variants** keeps your original and generates three distinct creative directions from it.
* **Product video** starts from scratch: brief, references to gather, storyboard beats, and video nodes ready to generate.
* **Audit canvas** inspects the whole board and suggests the highest-impact next creative action — the same idea as a full [canvas audit](/canvas/ai/canvas-audit).
* **Layout canvas** and **Organize selection** ask the assistant to frame and arrange nodes into a clean, readable workflow.

## Good to know

* Quick actions are prompts, not silent operations — each one opens the chat so you can watch the assistant work, steer it, or stop it. How much it confirms before acting depends on the assistant's [mode](/canvas/ai/plan-mode).
* Sometimes the assistant offers its own follow-up suggestions after a reply; when it does, those replace the default chips until the context changes.
* The dock is hidden for viewers on read-only projects, and while the full chat panel is open — the panel's composer takes over.

<Tip>
  Quick actions are the fastest way to learn what Flowy AI can do: select something, read the three chips, and you have a menu of its best moves for that context.
</Tip>