Skip to main content

​
Finished result

This nine-second Adesso concept shows the workflow in practice. Bloom supplied the brand system; Seedance rendered the 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

Connect Bloom to your agent

Setup for Codex, Claude, ChatGPT, Cursor, or any MCP-compatible agent.
Use this reusable starting prompt. It is not the original prompt used for the Adesso clip.

​
How it worked

1

Load the brand system

Retrieve the complete active Brand Skill from Bloom before making creative decisions.
2

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.
3

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.
4

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.

​
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.