Skip to main content
All projects

Self-correcting media agents · Media

Gemini Media Agents

Two self-correcting media agents built on the Gemini API and Google ADK. The image mockup agent extracts brand DNA from a style guide, generates two design concepts, renders each as a mockup with Gemini image, then scores the output against the guide and retries on failure. The video explainer agent turns a topic into a narrated, multi-scene explainer: Gemini image → Veo video per scene → evaluate → retry, then stitches the final cut with ffmpeg.

1 / 1

Highlights

  • Brand-DNA extraction + evaluator-scored image retries
  • Multi-scene explainer pipeline (Gemini image → Veo → eval)
  • ffmpeg scene stitching
  • Runs as plain CLIs against the Gemini Developer API

Tech stack

  • Python
  • Google ADK
  • Gemini
  • Veo
  • ffmpeg