I'm surprised that they don't just keep the various prompts, which are arguably their "secret sauce", hidden server side. Almost like their backend and frontend engineers don't talk to each other.

My company uses Claude through our own private data centers behind our own proxy that logs all requests and responses in and out. However, Anthropic heavily steers these models during RL to respond a certain way to certain prompting, so that's basically the "secret sauce" you're thinking of.

i always wondered what prompts codex / claude code use but always figured they just send variables to the backend and render the whole prompt there so i never even bothered to check with a MITM proxy. turns out i should have just done that…