At Octomind, we build AI agents - but our code is still mostly written by humans. We love LLMs and... Tagged with ai, agents, programming.

Dev.to is a community platform for developers, offering resources, discussions, and networking opportunities to empower individuals in their coding journey. Developers can learn new programming languages, frameworks, and tools, engage in discussions on best practices, and share their experiences with fellow developers to enhance their skills and grow their professional network.

An AI engineer shares hands-on experience testing coding agents like Cursor and Claude Code for a week-long feature implementation. Despite industry claims of 25-80% AI-generated code, the experiment revealed significant limitations: agents produced thousands of lines requiring extensive review, ignored coding conventions, made inefficient database queries, and confidently marked incomplete work as finished. Two critical issues emerged: developers lose their mental model of the codebase when AI generates large PRs, and AI lacks self-reflection to accurately assess its own capabilities. While useful for brainstorming, tab completions, and narrow tasks like unit tests, coding agents aren't yet ready to write most production code.

Why agents DO NOT write most of our code - a reality check

Experimenting with coding agents in day to day coding

Agree with this 100%. Maybe that is why I use the Chat with a prompt like “Optimize and refactor this method with an emphasis on security” or something “Analyze this code and let me know what possible security issues that you find”.
The only I use the Agent for is for documentation and unit tests ;-). Not my favorite thing to do.

Having agents write code is like rolling the dice. They’re alternate dev personalities on call 24/7. It depends on your project.
Edit: They’re no longer on call 24/7; they now have weekly limits.