The fact that Stripe are touting a production product that (at face value) benefits their business seems to suggest that maybe crap is subjective and as ever, being overly opinionated in an emerging space might actually be a blocking mindset rather than a positive one.

It might also suggest they went with the first LLM recommendation, like Anthropic choosing React for Claude Code.

Yes this paper even tries their enterprise case. Perplexity performs worse. https://arxiv.org/html/2604.17843v1

You can just look at nouswise or nblm. They do have such harness behind.

Wasn't using a source-grounded AI with citations a better natural choice than chatgpt with hallucinations?