About

I'm a software engineer, and this is a learning log from inside real projects. I'm figuring out how to use agentic AI as a coding companion while I think, design, debug, and occasionally get confused. It hasn't replaced me, and I don't treat it as an oracle. It's one more thing in the loop.

The name comes from the rubber duck: you explain your thinking to it until something clicks. Sometimes the duck helps, and sometimes it confidently leads you astray. Either way, the explaining matters more than the answers.

This isn't a tutorial site or a product blog, and I can't promise anything here is correct.

What you'll find instead:

- short notes from real work
- experiments that half-work
- failures that taught me something
- evolving opinions about agents, tools, and boundaries

Posts are written as things happen, not cleaned up afterward. My opinions will change, and old posts may age badly. That's intentional. I may even change the posting rules, but for now i have them published here.

If any of this is useful, great. If not, that's fine too. The duck and I will keep talking.