The Problem: The Claude 3.5 Sonnet model, used in Composer Agent mode, is incredibly capable, but still needs human supervision. Not because it can’t do the work, but because it needs simple reminders like “check your work” or “what did I say earlier?” to stay on track. Even with features like auto-…

Only after posting this did the forum suggest some other actually-similar posts: Watchdog for agent mode GPT-Style Agents/ Agent Teams

@lukemmtt Totally agree, this would be a game changer for Cursor!

@saketsarin @maxritter @funkenstrahlen @alejoh90 @dglewis @emmanuelkuebu Thanks for all the positive reactions all! Please consider hitting the “vote” button as well to give this post more visibility :heart:

Yes there are definitely cases where claude thinks it has found an issue which is an non issue. Some more structured approach guiding the evaluation process helps. cursor rule files for example, or otherwise local notes/details/requirements in regular .md files help to guide it. sure eventually the…

Aider showed that this is how you achieve the best AI coder agent. Also, an agent that implements this flow would be absolutely game changer for Cursor I think. So yeah, great suggestion!

@danperks Since this idea seems to have gotten some traction, I would be grateful to hear your take on it. Any internal discussion about this idea or similar?

Thanks for the suggestion! Its a really interesting idea and we have some experiments in this area that we’re working on, but nothing I can share just yet. Really appreciate you taking the time to write this up - its great to see the community thinking about ways to improve the product

it’s a good idea, this can be developed further. cursor can be very different. printing code with artificial intelligence can become even better. otherwise, as you said, we are constantly trying to keep the system awake contextually. this is frankly very difficult and after a while it already gets …

This layer of (overseer) orchestration is the only thing keeping me from trusting YOLO mode. I still wouldn’t 100% trust it, but it would be a huge promotion, taking the junior level mindset of agent, regardless of model used, to a more senior member. The layers and layers of rules that we have to p…

"Supervisory" agent to guide "worker" agent

Ideas Feature Requests

lukemmtt (Luke M) February 9, 2025, 7:20pm 2

Only after posting this did the forum suggest some other actually-similar posts:

Watchdog for agent mode
GPT-Style Agents/ Agent Teams

Topic		Replies	Views
Introducing an Engineer Agent Feature Requests	0	69	October 21, 2025
Coding agents—brains without judgment Discussions	1	168	May 11, 2025
Does Cursor support SubAgents? Feature Requests java	12	7837	July 27, 2026
This might help some folks with complex workflows: How to Use Cursor-Agent (and/or Claude-Code-SDK) from Inside Cursor IDE Guides	2	3332	January 28, 2026
Best way to integrate Cursor into an existing VS Code repo with Claude Code + Codex-style multi-agent workflow and automation? Help rules , context , subagents	18	1229	July 27, 2026

"Supervisory" agent to guide "worker" agent

Related topics