For a while, I kept seeing that the cost of writing code was approaching zero. So many people felt that with an AI LLM, the costs would go way down to produce software. I'm not sure that's true. In fact, some companies are finding they spend more on AI tokens than salaries.

However, the ability to produce more code, experiment with ideas, or generate proof of concepts has gone up. Whether it's worth the cost or not depends on the engineer, but some organizations are finding that they can try more things than they would ever had time to try in the past. The time of engineers was the constraint, and if you can afford the cost, AI LLMs can relieve that time pressure.

Maybe the ability to get more done with agents means you should follow one of your hunches in software. Maybe you should try something.

Be thoughtful in your approach, use the LLM wisely, and learn to guide it efficiently, but use it to try an experiment that you might not think you have time to explore. Try an alternative. Implement something in a new way. OR implement it yourself and set the AI loose, asking it to work in a different way. You certainly could tell the LLM not to use your approach and try something different.

To me, the big advantage of an AI agent is it gives me time, something that I see as the most impactful constraint in my life. I'd like to get more done, but I'm not willing to work a lot more. Using an AI agent with a measured approach lets me tackle things that I might not otherwise get done. Certainly not as quickly as I get them done, and certainly not without stealing some personal time.

I get more done at work, without working more. I'm not working less, but I'm more effective. That's what I've always aimed to do.