ok1984

If you architected your code in a consistent way and are good in reading and reviewing code; AI can definitely help you move much much faster than if you write the code yourself, so while the AI is working on your current prompt you can move your focus on the next thing.

I consider myself a fast coder, but there is no way I can code faster than AI. But my rule is that even if AI wrote the code I still review and own 100% the code.

The main issue is that many managers are selfish, if you are a technical talent they prefer to keep you locked in the technical side because you make their life easier, you could state clearly your intentions for example: within the next three years I want to move from the technical side to the management side and define with your manager and future manager what should be done to achieve this goal making it clear that if it doesn’t happen you will be willing to seek other opportunities outside your company.

It is your company that should provide guidance to what you should do to achieve this goal, some companies might offer you a master or MBA.

Doing certificates and studying can help increase your knowledge and could be helpful if you seek such opportunity outside of your company but if you plan to stay in your current company it’s better to let them define what is needed so they don’t have excuses.

Read and review it!

Based on personal experience, who ever tells you it is easy is lying to you.

Kids are amazing and you don’t realise it until you have your own, on the same time they require a lot of physical and mental energy especially if both parents work; so be prepared to lower your expectations, I don’t remember who said it but in life you can do your best in two things at most: work, family, social, sport just pick two, don’t expect to be able to do everything.

You will have some sleepless nights, sometimes your plans will drift, don’t fight it and be ready to be flexible, if you had a sleepless night the next day at work pick something easy, on good days do the complex work because you don’t know what will happen tomorrow.

You will have to orchestrate your life around things you cannot control such as when kids are ill and most importantly whenever possible to get or ask for help just do it don’t feel ashamed of asking for help.

Finally, if you plan to have a second kid, I suggest to avoid waiting too much, it’s better to have them with a two-three years distance so that once they are old enough you can focus on what you left behind when they were young and remember they grow so fast so make the most when you are with your kids personally I prefer spending time with kids rather than having an ordered house ;)

TDD advocates would be proud of you ;) differently from your approach I still prefer to make sure the model code is inline with my expectations and only then ask for unit tests, only exception is when I am dealing with a bug then the failing unit test is a MUST.

Yes, its like when you are chatting with somebody and due to the async process somehow you start chatting about two things in parallel (maybe it’s only me),

Anyhow, I think that you can keep in the flow as long as the successive prompts are still related to the major change if not then I guess you deserve a stop and pause before moving on with the next task.

My process is becoming as follows:

1) I always start with a clean code base (ie. no uncommitted changes)

2) I have a text file called prompts in which I write my first prompt for my desired change, in the initial prompt I always explicitly ask to NOT generate unit tests.

3) Copy paste the prompt to the cli

4) While the LLM is working on my prompt I go back to my prompts file and start preparing the next prompts that will build on top of the previous one

5) Once the agent is done I review every single line of code and either manually fix what I don’t like or prompt minor changes until I reach my desired result.

6) commit locally the change

7) copy paste the next major prompt from my prompts file

8) Repeat steps 4-8 until I fully implement my major change

9) Once I have my major change I prompt for adding unit tests and related documentation

10) Once my unit tests are all green I execute additional manual tests if required, squash all local commits and push for pear review

Following these steps I can work fully focused and let me emphasise again on the fact that even if the majority of code is written by the LLM I still review and read every single line of code so that when LLM companies decide to fuck us or when shit happens in production I know where to look as if I wrote the code myself like the old days

All of this works for me because I know very well the programming language and the specific domain I am working in thanks to the past experience collected in past years before LLMs.

That I get instant hot water in my shower every time I need it :D

Of course, you might have the best product in the world, but if you are an a* then I will buy somewhere else even if that means pay more or not use the service at all.

I don’t understand why, some people have fun doing their job and feel joy when blogging about products they create and believe in, for me it’s a hubby.

Wish you joy and happiness in your live.

Biggest discovery is that humans are much worse than expected, and are always rushing to the next big thing forgetting to enjoy the present.

Seriously shouldn’t the whole world slow a bit down and enjoy our lives a bit?

For me automating release notes is like recording an audio and play it each time you introduce your kid to somebody.

You worked hard you added all those new features and fixed several bugs and hopefully introduced no new ones, take the time and write the release notes yourself or with the team, make it a moment of celebration, read them and refine them (even with LLMs) but be proud of what you just accomplished.

For me writing release notes is a joy moment why should automate it?