Set up a coding environment with 'guardrails' like TypeScript and linters, then use a simple prompt in Cursor to let its AI agent automatically find, analyze, and fix code errors. This workflow streamlines debugging and improves code quality.
with Claire Vo
Before using the AI, configure your project to define what 'good code' looks like. This gives the AI agent context to effectively debug. Set up four key systems:
1. **A Typed Language**: Use a language like TypeScript to enforce strict data types and catch bugs early.
2. **Linters**: Integrate a linter to scan your code for style mistakes, bugs, and bad practices.
3. **A Formatter**: Use a code formatter to automatically standardize indentation, spacing, and line breaks for consistency.
4. **Tests**: Write automated scripts to confirm your code works as expected, ensuring changes don't introduce new bugs.
Once your guardrails are in place, instruct the Cursor agent to fix problems with a high-level command. The agent will use your project's tools to execute, analyze, correct, and verify the fixes on its own. For example, it will run your linting command, read the error output, navigate to the correct file, apply the fix, and re-run the command to confirm the issue is resolved.
fix the lint errorsTurn complex, repetitive tasks into custom commands. Use the @ menu in Cursor to reference your current changes (e.g., @branch) and create a detailed prompt that tells the AI to review those changes against a specific checklist, such as checking for security, performance, or testing best practices.
Review all the changes I have on my branch (@branch). Were there any changes here that could affect if the application is running offline? Did we add good tests? Did we make any changes to authentication?
Follow Sahil Lavingia's method for delegating small but impactful maintenance tasks, like fixing an internal Slack report, to the AI agent Devin. This workflow shows how to use simple, clear prompts to fix code and update system prompts without distracting your engineering team.
Learn Gumroad CEO Sahil Lavingia's process for rapidly prototyping a UI with v0, then using the AI agent Devin to autonomously code, implement, and submit the feature for review, turning a multi-day task into a one-hour workflow.
Improve your writing in real-time by using ChatGPT as a first reader. Get instant feedback on structure, clarity, and flow as you write, allowing you to polish your work section by section.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.