GPT6 Astra Motion Graphics Full Tutorial (After Effects)
Demystifies agentic desktop control and MCP workflows in Adobe After Effects, showing AI filmmakers and motion designers how to automate tedious UI animations and screen graphics into fully editable project layers.
What this lesson covers
Rourke Heath explains how to integrate GPT Astra with Adobe After Effects to generate editable motion graphics and SaaS promo animations automatically. He details the required computer-use permissions, usage costs, and prompt workflows using UI screenshots and video recordings.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 01:05 ↗
Running an automated motion graphics task in GPT Astra takes approximately 10 minutes and consumes about 2% of monthly usage credits on the $100/month plan.
- 02:24 ↗
ChatGPT controls After Effects projects directly by enabling the Computer Use plugin, toggling MCP, and granting OS accessibility and screen recording permissions to Codex.
- 03:40 ↗
GPT Astra can track graphics onto existing video plates or generate animated compositions from scratch on a blank After Effects canvas in a single generation.
- 04:47 ↗
Providing static UI screenshots alongside prompts detailing logo animation, motion blur, and editable layers generates functional multi-layer After Effects timelines.
- 06:12 ↗
Supplying a screen recording walkthrough allows the model to interpret user interactions, sliders, and navigation flows to build matching transition sequences.
Workflow outlined in the video
- Install the ChatGPT desktop app and select the GPT Astra model in the work tab.
- Navigate to plugins in ChatGPT, find Computer Use, and toggle on 'Enable MCP'.
- Open operating system Privacy & Security settings and grant Codex Computer Use permissions for screen recording and accessibility.
- Launch Adobe After Effects and create a blank composition (e.g., 1920x1080) as the staging canvas.
- Upload reference assets (screenshots, Figma files, or video recordings) to ChatGPT with specific instructions requesting editable layers, smooth keyframing, and motion blur.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
20,790 views captured 30 September 2026. ReelStack recommendation score: 46/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 65% performance: 0.48× current views vs the channel's recent median; same-age history is not yet available. View-evidence factor 95% (views / (views + 1,000))
- 25% freshness: 92/100 with a 14-day half-life
- Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
- 10% engagement: 32/100; likes + 4× comments, smoothed with a 500-view neutral prior