how i've been using cursor in the last month

1. always use plan mode

(did this a lot before it was native in product) to gather relevant context and align on the problem/solution with model before executing 2. prompt for self-verifiable solutions the agent can run. if agent can see and reason about what it does, it can detect divergence from plan or what you prompted for in the first place. browser use is the clearest example of this. however, it can also create tests/scripts to verify runtime in all sorts of systems

some custom commands you can try out

define them in .cursor/commands/[command].d and they'll show up whey you type slash. lmk if you have other ones that are useful! 1. light code review

```md
Perform a light review of the current diff from this branch against main using `git` and commands in package.json

Goal of review is to find critical security and performance bugs.

If you find any issues, take not with a suggestion for improvement
```

the best rules in @cursor_ai aren’t the ones you plan. it's the ones you stumble into doing something manually, realizing it’s repetitive, and capturing it as a rule

here’s a overview of the 3 main types of rules i've seen (and use myself) ↓ 1. workflows

step-by-step instructions for how cursor should behave in specific situations. written in natural language

https://twitter.com/505835394/status/1928224127942545605

get a lot of questions on how to use @cursor_ai in large codebases and monorepos. while it depends™, here are some tips and tricks enable project structure to make the model more aware of how the project is structured

i've built 10+ internal tools at @cursor_ai using cursor. when you have a platform in place, it makes it so easy to spin up new tools

here's how ↓ the first piece is to have the primitives in place like database, servers, networking, workers etc

i've setup this on aws with terraform

rolling out @cursor_ai 0.49

here’s what’s new ↓ you can now generate rules from conversation using the command /Generate Cursor Rules

great way to capture decisions from back and forth chats you might want to reuse later

i asked some people at @cursor_ai how they use cursor

some nuggets in here ↓ @shaoruu
- create dedicated "playgrounds" to iterate on the ui/ux or logic with the ai, kinda like a free-roam space until you get something you like, and then integrate it back to your main app

- use @ pr and @ commit to review changes & undo things you don't like

context management in @cursor_ai is key to getting the results you want

here are some of the @-symbols you can use to make sure you include relevant context in your prompt ↓ use @files and @folders to explicitly reference specific pieces of code. great when you know what code you want to include. personally, i always include specific files when i know what i want to change

we've been hard at work improving @cursor_ai Agent, allowing you to delegate more tasks and let it work alongside you

agent works just like a human developer, with access to your tools, codebase context, and the ability to take actions

here's what Agent can do ↓ using tools, Cursor Agent have the capability to reason about when it should
- read & write code
- search your codebase
- call MCP servers
- run terminal commands

an example where it connects to a postgres database, runs a query and writes to file