bayu

I ve been building NAEOS around a question:

What happens when AI coding agents move from write some code to actually participating in software engineering?

Most AI coding tools are getting very good at generating code.

But production engineering involves much more:

AI coding agents are getting incredibly good at writing code.

But while building with them, we kept seeing the same problem:

The agent knows how to code, but doesn't always know how the system should be engineered.

Architecture decisions, security rules, testing standards, project conventions, and engineering context are often scattered across repositories, docs, and people's heads.

Most introductions start with what someone is building.

Mine starts with a problem I kept seeing:

Docs say one thing. Code says another. And every new engineer has to figure out what actually happened.

I've spent a lot of time experimenting with AI coding agents, and they made this problem even more interesting.