You can now work with Cursor Agents on web and mobile. Just like the familiar agent that works alongside you in the IDE, agents on web and mobile can write code, answer complex questions, and scaffold out your work.
Now with automated code review to catch and fix bugs in your PRs, memories to learn from your codebase, 1-click MCP installs, and Background Agent in GA. Plus, faster multi-location edits, richer chat interactions, new settings, and Jupyter notebook support.
There's a lot of options for models these days. I've been using Claude 3.7 but I'm curious what's been working well for others. What model are you using and why?
Is the thinking version of @Claude by Anthropic worth the extra credit spend? Does @DeepSeek work well enough to save some credits? Is it worth trying any of the @ChatGPT by OpenAI models?
At @Bucket, we're always looking for products that can boost productivity and inspire us to build better software. We recently experimented with @Cursor to replace @Github Copilot.
Key takeaways
Tab completion: Cursor includes a helpful tab completion feature, suggesting refactorings and improvements as you go huge time saver!
Chat: the chat/composer is better than Copilot as it can modify across files in the codebase. However, we still needed to correct the code most of the time :/
Full context: Cursor has full context, so it provides more helpful advice and changes
Generating comments: it makes it easier to add code comments they need clarifications from time to time tho
Working with existing codebases: Cursor seems better at writing code from scratch than contributing to large existing codebases
Hallucinations: as far as we can tell, it had fewer hallucinations compared to alternatives
Prompting strategies: being somewhat specific in prompts by referencing classes and functions seems to work well We're currently experimenting with `.cursorrules` files to improve prompt quality
Recently started consulting with a startup, and I ve fully switched to Cursor for all my PRDs and PM needs no more Google Docs or anything else. I ll never go back!
With MCP, I ve even connected Google Docs, just in case I ever need it right inside Cursor itself, haha.
Oh, and I m nudging the devs here to try Cursor too slowly moving them away from Copilot.
Cursor 1.7 is here! Introducing autocomplete for agent, hooks, team rules, ability to share prompts with deeplinks, and more. Look forward to hearing what you think!
To be honest, I find Cursor s VS Code experience quite uncomfortable. However, the fact that it runs seamlessly within my codebase is what keeps me from abandoning it.
That said, if Copilot were to offer the same level of integration, I don t think I d continue using Cursor. Copilot is gradually catching up with the features Cursor provides, and it works within IntelliJ, which is a big advantage for me.
A more powerful version of Copilot that can suggest mid-line completions and entire diffs. Trained to autocomplete on sequences of edits, it's quick to understand the change you're making.
