Using Copilot for code review is surely just a gimmick.
We already have tools that do *deterministic* code quality analysis using far fewer resources.
I just can’t square:
“Because Copilot code review is powered by a large language model, it can help with enforcing coding guidelines that are not covered by your linter or static analysis tool.”
with:
“Copilot isn’t guaranteed to spot all problems or issues in a pull request, and sometimes it will make mistakes.”