(agentclientprotocol.com)

270 points vinhnx | 1 comments | 30 Aug 25 12:42 UTC | HN request time: 0s | source

Show context

mg ◴[30 Aug 25 14:02 UTC] No.45074786[source]▶

I'm fine with treating AI like a human developer:

I ask AI to write a feature (or fix a bug, or do a refactoring) and then I read the commit. If the commit is not to my liking, I "git reset --hard", improve my prompt and ask the AI to do the task again.

I call this "prompt coding":

https://www.gibney.org/prompt_coding

This way, there is no interaction between my coding environment and the AI at all. Just like working with a human developer does not involve them doing anything in my editor.

replies(2): >>45074878 #>>45076374 #

1. zarzavat ◴[30 Aug 25 17:21 UTC] No.45076374[source]▶

>>45074786 #

I don't let it commit. I almost always need to modify its work in one way or another.

Most of the time I don't bother reprompting it either. If it doesn't understand the first time then I'm better off making the change myself, rather than sink time into a cycle of reprompting and rejection.

On the other hand, if it understands what I want the first time I have more confidence that it's on the same wavelength as me.

↑

Agent Client Protocol (ACP)