I actually did the same pilot for a couple of days, while I don't like codex reply, it tackled some problems that claude were spinning for 20 minutes in 5 minutes. Now I have them side by side for codex to review claude's plan and it always find something that claude missed. The reply and the format though is not as good as claude. Pros and cons really, there are many cases where claude weren't able to debug prod issues like codex did as well for me