I believe one of the reasons I’ve been pretty successful in adopting and utilizing Agents iny engineering work is relying on the decades of hard fought knowledge, experience, and taste. How do folks without that get it in this age of AI?

It’s unacceptable for me to say “AI is only for seniors and above” or other nonsensical takes. Here’s what I’m currently thinking. And as with most everything “rethought” for the AI era, it’s the same as before.

Appropriate scope

It’s unreasonable to expect a junior dev to architect an entire new service, or even feature. Continue to provide appropriate work, but allow for AI to help with even those small tasks. Thorough planning helps even with a small bugfix. You can provide critical feedback to the agent on test case edge cases, etc. It’s training for the big stuff but at a smaller scale. The same as its always been.

Apprenticeship

I read this recently and it really resonated with me. The concept is to have a junior and a senior work closely together for an extended period of time to learn first hand, day to day on how the senior operates.

One reason I find this super compelling is that there are many things that I do throughout the day that I would never think to capture in a training or lunch ‘n learn. Probably a lot of them I don’t even know I do.

Also, I love watching and learning from people more skilled and experienced.

I’m not worrying too much about new people coming up missing some aspects of the job that I know. The good ones will learn what they need and ignore all the extraneous crap that I’m burdened with ;)

Happy learning!

– Chris