[rqtwteye]

I look forward to most tech writing done with AI. Writing documentation and requirements requires a lot of effort to keep consistent and up to date. Having an AI look at your code and config and then write a nice report will easily beat 99% of all tech docs in companies.

[now__what]

I'd love for this to be the case, but often the most(/only) important part of a tech doc is the "why," i.e. the background knowledge about the business itself, or the conceptual framework that underlies the code. Even more so for writing requirements. How would AI be able to help with that? Maybe by parsing through all related meeting transcripts as well?

[popinman322]

> Maybe by parsing through all related meeting transcripts as well?

Those and design docs. It can also reason over code somewhat; it may be possible for the model to intuit design constraints from code.

[layer8]

This will be like auto-generated javadoc all over again, just more wordy and with contrafactual fabulations sprinkled in.

[rqtwteye]

I have thrown a set of our requirements and some helm charts at it and the summary it produced was pretty good. It needs some work but I think it’s just a matter of time until the output is pretty good. The bar for most documentation is pretty low.

[layer8]

The GP was about producing documentation from code. The problem is that useful documentation is exactly about what is not clear from the code.