Lab

Experiments and questions about software engineering, architecture and increasingly capable development agents.

LAB-001

AI-assisted PR review

Running

Can AI review materially improve pull-request quality without increasing review noise?

AI engineering code review quality

LAB-003

Agent architectural compliance

Planned

Can machine-readable architectural constraints outperform natural-language instructions?

architecture constraints AI tooling

LAB-002

Repository context for coding agents

Idea

What minimum architectural context does a coding agent need to make consistent system changes?

architecture AI-native development repository design