Agent systems @spacexai, prev @cursor_ai, love @chelseafc | Thoughts are my own, and so nuanced and cool, heck yeah
Joined July 2026
- Tweets39
- Following128
- Followers89
- Likes36
Jon retweeted
Once you use a modern harness (e.g., Grok Bot, Cursor Projects), you just can't go back to Chats.
Traditional LLM chats are dead, they had a good run from 2022-2026!
We find the users who send the majority of their messages in projects merge 6x more PRs vs non-projects users.
Projects also helped teach me to delegate and validate the same way @bot does
Honestly if you're not using @cursor_ai Projects you're just missing a ton at this point. Don't sleep on it. Give it a try and see how it significantly improves your life. Here are some tips for you. I'm using it since it was debuted internally:
* Have a single `Hub` that acts like a office manager. Use it for best practices, ask it to investigate how each project is working, what's missing? What can be done better? It there to help you and getter better
* Start with a few projects first, don't overdo. With time you'll understand how many is enough. For example I recently started a debug session for some of our Cloud Agent nodes, I knew I was going to create multiple agents, review agents and so on. So I created a single Project just for this purpose
* Make sure to use a proper model. Grok 4.7 is pretty good do the Project coordination part. I also use it for all kind of chores. If I need a big hammer, it dispatches agents with Opus/Fable. Cursor is nice because you're not bound to a single model!
* Give more autonomy to your coordinators. Share that you "don't want to be bothered" , ask upfront if there are any MCP logins, or website auths needed for the work to be done. Remove all self inflicted blocking, and then let it rip.
* You can assign nice icons and colors, choose them deliberately, it'll help during context switching.
* Enable remote workers. By default Projects runs in Cloud Agents, but suppose there is something to be done that can be only on your localhost, the coordinator can dispatch an agent that runs in your machine.
For more details read cursor.com/blog/projects and also my blog post arslan.io/2026/09/11/how-i-m…
Having Fatih, one of my fav follows for a while, now be working on cloud agents, my fav team, feels like a cosmic blessing
From watching you on book youtube to seeing this intersection with something I work around is really cool
For all my cloud agent folks who were looking for: more disk space, easier path to develop on macOS/iOS or other custom hardware, or a bunch of other reasons, Self hosted might be the answer
All the most productive people I know have a sweet edm playlist they listen to.
Makes me think I’m missing out by just having a rotation of 3hr video game lore explained videos in my ears all day instead of this rufus du sol character
Jon retweeted
It's been really fun leveraging @bot for GTM! Have spent a few weeks iterating on some of my workflows, so I wanted to share how I use Grok Bot at SpaceXAI.
My colleague @poteto just did an hour long session on creating systems that build trust in agent output.
Speaking to, I think literally, hundreds of customer, implementing some form of verification, testing structure into your ✨Software factory✨ is the highest ROI thing you can do. Trust is essentially the bottleneck and Laurens work is the best solution I've seen to this so far.
That and /bro
maven.com/p/e23d9c/how-curso…