We built a governance layer for AI-assisted development (with runtime validation and real system)

#ai #github #softwareengineering #softwaredevelopment

I’ve been working on a project called Janus — a governance layer for AI-assisted development systems.

The core idea is simple:

Instead of evaluating performance, we evaluate governance through evidence and protocol conformance.

We just published the second paper, which moves from the theoretical model to measurable governance:

Paper 1 (model):

Paper 2 (validation):

There’s also a live system running on top of it:

And the framework used to run it:

I’d really appreciate feedback — especially from people working on observability, event sourcing, or AI tooling.

DEV Community