How to build a coding agent
It's not that hard to build a coding agent. 300 lines of code running in a loop with LLM tokens. You just keep throwing tokens at the loop, and then you've got yourself an agent.
I'm a software engineer who writes about AI-assisted software development. I created the Ralph loop, which runs a coding agent in a loop until the work is done. It's the technique loop engineering grew out of.
Visit ghuntley.com → RSS feedOn Hacker News Feb 2021 – Oct 2026
Software Engineering 4Life, Learning & Writing 3Tools & Productivity 2Security & Privacy 2AI & Machine Learning 2Systems & Performance 1
It's not that hard to build a coding agent. 300 lines of code running in a loop with LLM tokens. You just keep throwing tokens at the loop, and then you've got yourself an agent.
These LLMs are shockingly good at deobfuscation, transpilation and structure to structure conversions. I discovered this back around Christmas where I asked an LLM to make me an Haskell audio library by transpiling a rust implementation. An “oh fuck” moment in timeOver the Christmas break I’ve been critically looking