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

# Create a branded product video

> Use a brand in Bloom and a connected agent to brief, render, and review a short video with Seedance or another video generator.

## Finished result

This nine-second [Adesso](https://adessobakeshop.com/) concept shows the workflow in practice. Bloom supplied the brand system; Seedance rendered the video.

<video
  controls
  playsInline
  preload="metadata"
  src="https://mintcdn.com/bloom-100885a1/0YDI4N4iz9GbHbHU/videos/use-cases/adesso-branded-product-video.mp4?fit=max&auto=format&n=0YDI4N4iz9GbHbHU&q=85&s=83073968c442771891bd0c341c956d9d"
  poster="/images/use-cases/adesso-branded-product-video-poster.webp"
  alt="Nine-second vertical Adesso product video rendered by Seedance"
  aria-label="Nine-second vertical Adesso product video rendered by Seedance"
  style={{
width: "100%",
maxWidth: "360px",
aspectRatio: "9 / 16",
display: "block",
margin: "0 auto",
borderRadius: "0.75rem",
}}
  data-path="videos/use-cases/adesso-branded-product-video.mp4"
>
  Your browser does not support video playback.{" "}

  <a href="/videos/use-cases/adesso-branded-product-video.mp4">
    Download the Adesso video
  </a>

  .
</video>

## What you need

* An agent connected to Bloom through MCP.
* A ready brand in Bloom.
* Access to a capable video generator, such as Seedance.

## Run it with your agent

<Card title="Connect Bloom to your agent" icon="plug" href="/mcp/connect" horizontal>
  Setup for Codex, Claude, ChatGPT, Cursor, or any MCP-compatible agent.
</Card>

Use this reusable starting prompt. It is not the original prompt used for the Adesso clip.

```text theme={null}
Use Bloom through MCP to make a short video for [brand website].
Video idea: [video idea].

Reuse a matching ready brand, or create one in Bloom and wait until it is ready.
Inspect the complete active Brand Skill. Translate the relevant identity,
voice, imagery, and constraints into one focused motion concept.

Decide whether a small number of relevant rendered assets would help. Use
references only when they serve the concept. Write a concise brief covering
duration, framing, action, pacing, sound, and what must remain unchanged.
Give the external video tool only the prompt and assets it needs, then generate
the video.

Compare the result against the Brand Skill and refine only if needed.
Do not publish anything externally without my explicit instruction.
```

## How it worked

<Steps>
  <Step title="Load the brand system">
    Retrieve the complete active Brand Skill from Bloom before making creative
    decisions.
  </Step>

  <Step title="Distill it for video">
    Turn the relevant guidance into a motion brief. The agent reads the full
    Skill; the video generator receives only the focused prompt and useful
    assets. Raw font files are not useful inputs for a video model. If
    typography matters, use rendered references.
  </Step>

  <Step title="Render in Seedance">
    Seedance renders the clip from the brief and any chosen references. The
    Adesso example used a reference image; other concepts may not need one.
  </Step>

  <Step title="Review and refine">
    Compare the video with the Brand Skill. If it misses the brief, adjust the
    prompt or references and render again as needed.
  </Step>
</Steps>

## What each system did

* Bloom held the durable source of brand truth and the current active Brand Skill.
* The agent chose the concept, prompt, and assets, and handled review.
* Seedance rendered the video.

## Before you publish

* Check brand fit against the Brand Skill.
* Look for malformed logos, incorrect text, and product or subject deformation.
* Watch for visual artifacts and check framing throughout the clip.
* Listen to the sound and check that it fits the intended use.

This is independent concept work, not an official Adesso campaign.