Our AI policy is to allow AI-generated code, but only after several rounds of my manual review.
My own AI usage is limited to docs, changelogs, some tests for corner cases.
Nothing too crazy.
But, we develop a lot of AI tooling for end users: skills / MCPs / evals / contexts / etc. That’s why these ignores are needed :)
As somebody who does the inverse (keep AI away from docs, changelogs, … really anything intended to be read), how to you get good output for those documents?
I would love to have docs autogenerated to some extend from my extensive engineering notes, but I find the writing always terrible so I have to rewrite everything anyways.
My process is that I run top Claude model on the small set of changes to reflect it in the docs. I get like 80% from there and then I polish it by hand. Remove bad wordings, change examples, cut whole paraghraphs of text, etc.
I tried different “skills” for writting, but I never got any good results from them :(
surprising self-awareness
score 1 · canonical
Our AI policy is to allow AI-generated code, but only after several rounds of my manual review. My own AI usage is limited to docs, changelogs, some tests for corner cases.
Nothing too crazy.
But, we develop a lot of AI tooling for end users: skills / MCPs / evals / contexts / etc. That’s why these ignores are needed :)
score 1 · canonical
As somebody who does the inverse (keep AI away from docs, changelogs, … really anything intended to be read), how to you get good output for those documents?
I would love to have docs autogenerated to some extend from my extensive engineering notes, but I find the writing always terrible so I have to rewrite everything anyways.
score 1 · canonical
My process is that I run top Claude model on the small set of changes to reflect it in the docs. I get like 80% from there and then I polish it by hand. Remove bad wordings, change examples, cut whole paraghraphs of text, etc.
I tried different “skills” for writting, but I never got any good results from them :(
score 1 · canonical