Hey everyone! During last night's community call, we started sharing some awesome Cursor AI tips and tricks, and realized we should capture all this great insight in one place! I decided to create this post to gather all of your best Cursor AI tips, tricks, and workflow hacks. Afterward, I'll compile your contributions into our first-ever community-driven video for the YouTube channel. To get the ball rolling, here are 5 tips I've found incredibly useful: Tip 1: AI Model - Gemini 2.5 pro is the best model I've ever used. It does exactly what you ask most of the time. It doesn't wander off and do random things too often. It can also solve complex problems. Its context window is huge, so you can pass in a bunch of reference files for context. Tip 2: Cursor Rules - If you notice the model keeps making mistakes, update your cursor rules to instruct the model on what it should do. Tip 3: Open multiple chat tabs - When I'm working on a project, I like to go speed mode. While Gemini 2.5 pro is solving one problem, I open an extra tab to tackle a different problem. Usually, I have 2 to 3 tabs running AI simultaneously. It's like managing a team of engineers, constantly reporting back their work for approval or feedback. Tip 4: @docs - When consistently working with a new library or copying code examples from a specific page, I add that web page as an external doc. Just type @web followed by the link, and then you can ask questions about the docs. Tip 5: Create an ai_docs folder - I store my holistic project plan here. This plan outlines my high-level goals, tasks, and the reasons behind them. It’s a living document that I continuously update. When I open a new chat in Cursor, I easily reference this document. For large tasks, I create specific task documents containing detailed goals and subtasks. I create these documents with AI and then we tackle the subtasks together. Now, it's your turn. What are your favorite Cursor AI tip or trick? Drop in the comments below!

Hi all, I am currently working on to develop a troubleshooting crew which uses kibana/elastic search tools and can be able to troubleshoot the given issue. I am stuck in handling at large tool outputs since kibana/elastic search data is huge. Let me know any suggestions on this.

Sam has a great video released yesterday where he discusses how to use this new agentic framework to build a research tool. https://www.youtube.com/watch?v=MkqkiJgnDxk

tl;dr: Newb should use: venv, conda, poetry, Crew's "crewai install" command, docker containers? I'd love to hear what you recommend! @brandon I believe you prefer Conda ... why? [I've installed anaconda and can use that]

Request help for Building a chatbot for Log analysis using LLMs The Motivation is as follows: There are many industrial applications that use various systems (devices). It is these logs that are analysed by the engineers to study the functioning, performance and maintenance. This exercise is resource intensive. But it is unavoidable because there is deep reasoning and logic behind the analysis and is based on the industry specific knowledge and domain expertise and is currently done by humans.For standard devices like our computers, we have system logs, event logs and application logs. For analysing these logs, there are many commercial and open source applications since these logs follow a standard format. However, for proprietary systems like the one I am building for, the logs follow a custom format and these formats may have custom entities and descriptions. Of course, there is a document that has the Business logic and knowledge embedded in the logs that explains these custom logs in detail i.e. events codes, Alarms, descriptions, etc. This coupled with the "How to perform log analysis" document and product design document will help to understand why a device behaved in a certain way. My main goal is to provide a chatbot application that can use an LLM to extract key insights from log files. Essentially, provide a simple user interface where the upper management (Non technical staff) can ask questions and get a response. i.e. 1. When was the last time Device A generated the following events/alarms ? 2. In the last 30 days, how many times did Device B log the following error "<error description> 3. When the <error> was logged by Device A, was Device B in working condition? 4. Why did Device C generate the alarm at <time> on <date>? 5. Generate an error report for Device D in a tabular form with date time and the event with causation and its consequences on other devices? 6. Generate a summary report for the entire system for the month of <month>?