Subscribe
Sign in
MindPal
p/mindpal-aiBuild AI multi-agent workflows to automate any tasks
Start new thread
Tham (Sylvia) Nguyen

What can we learn from leaked system prompts of Manus, Cursor, v0, and other top AI agents?

by

I recently came across this Github repo which shares the system prompts of top AI agents on the market: Manus, Cursor, v0, Lovable, Devin, Windsurf, and more.


After studying them, I found there are 5 core principles that underpin all of these system prompts, and make their AI agents so good.


I call them the STARE framework ↓


Here's a breakdown of what they are along with exact examples and tips you can use: https://mindpal.space/blog/5-prompting-lessons-system-prompts-manus-cursor-top-ai-tools-6f4e8a


How about you? What are your takeaways? Share below!


53 views

Add a comment

Replies

Best
Lee Pri
This is a fascinating breakdown, thanks for sharing the STARE framework. It's intriguing to see how structured prompting strategies can lead to such high-performing AI agents. I’m especially curious how these principles might evolve as agents become more autonomous and adaptive. Definitely bookmarking the article for a deep dive.