Author(s): Mayank Bohra

Originally published on Towards AI.

Stop using generic AI chat. I’ve built a specialised toolkit in Cursor using GPT-5, Claude 4, and Gemini 2.5 to match the right model to the right job. Here’s the entire setup.

I got tired of the one-size-fits-all approach to AI in my IDE. Just having a single chat window feels like hiring a brilliant intern and asking them to be a senior architect, a QA lead, and a security expert all at once. It just doesn’t work. The real leverage comes from specialization.

This initial set of seven modes forms the strategic core of my AI toolkit. They handle the high-level “thinking” tasks: architecting, planning, debugging, and optimizing. By delegating these complex cognitive loads to the right specialist model, I can maintain a clearer headspace and focus on the bigger picture. However, a great development workflow also requires hands-on experts for execution, documentation, and security, which will be addressed in the next post covering additional modes for research, security, code review, troubleshooting, API design, database expertise, and DevOps assistance.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI