I keep improving my agentic feedback loop
I keep improving my agentic feedback loop.
A feedback loop is critical because it helps the coding agent see if it made any mistakes.
My feedback loop is an npm script called 'check'.
It *concurrently* runs:
- tests
- lint
- spell check
- prettier
- build
Takes ~5 seconds.
A good check script is basically like running a local CI check. If the check script passes, I can be confident the code will actually run and is now ready for a human code review as a final approval step.