When Your AI Agent Just Goes Off and Does It
Imagine you pose a casual question to a colleague about their approach to something - not expecting them to actually do it, just wanting to understand the method. A few minutes …
Read the storyThe Kodelet blog
Blog
Field notes on building Kodelet, working with coding agents, and learning along the way. Experiments, useful patterns, and the occasional unexpected result.
Building a Meta AI Agent: The Understated Power of LLMs in a Feedback Loop
It looks like magic when you witness AI agents autonomously viewing files, making edits, executing commands, and working around errors. However, under the hood, the core loop is …
Read the storyRunning an army of AI coding agents on the CI
Table of Contents Overview TL;DR Background Climb The Complexity Ladder Just Do It Implementation Conclusion Acknowledgement Overview This post explores how to deploy and manage …
Read the storyPrompt Techniques I Like for Coding
I’ve been programming using AI Agents tools such as Cursor over the past year, and Kodelet (a tool I dogfood myself) lately exclusively. Looking back, it’s remarkable how LLMs as a …
Read the storyLess noise, more field notes. Subscribe via RSS →