A post I saw the other day from someone in a similar situation who did share what changes were made: https://bsky.app/profile/abumirchi.com/post/3meoqzl5iec2o

To be a little less vague - I think the biggest difference I’ve seen is where time is spent. In the past since I know what I’m doing I’d go straight into dev mode pretty quickly .

Going straight into dev mode with an LLM pretty much always goes wrong - a lot more time is spent in planning and in setting up constraints for how an agent can operate before letting it loose so that once you set it free it can run.

It’s a crude comparison but it’s a lot more similar to what I’ve done in my management roles than what I’ve done as a dev.