Which AI tool do you use for documentation?

I don't use AI for documentation.

For serious projects I will usually run separate hardware and software documentation  streams.

The documentation starts before and CAD or IDE are used.

The idea is to describe things before the tools start to get in the way. As the design progresses you develop the documentation and then the code/schematic etc.

For example - if you will use a micro-controller you need to decide which one. To make a good choice you need to know what it is going to do - and the design notes (as I call them) are used to develop ideas and define them in increasing detail.

It is generally accepted that very early design decisions often define most of the project - and so they are very important. If you use AI to do this you will have delegated most of the cost of the development in that first one page description you give the AI.

Of course documentation written after the event is crazy - if you have to describe the design when its complete it should prompt you to at least wonder how you got there !

I can't see where AI comes into a good design process - except as maybe a spell checker.

I suspect that I am already in a minority - welcome to the 20230s - where AIs will use terawatt hours  of energy to produce peta Pages of output which other AIs will summarise down to .......

MK

I really like your point of view. I agree that documentation should start from the beginning of a project instead of being written only after everything is finished. It also helps explain why certain design decisions were made, not just what the final result is.

I don't think AI should make important engineering decisions either. For me, AI is more useful after the planning stage. It can help organize notes, improve writing, create summaries, or make documentation easier to read, while the engineer still makes all the important decisions.

I think AI works best as a helper, not as a replacement for the engineer.

I started my technology career in 1981. Entering a site required a sign-in and sign-out. Every action taken on the site or work on the equipment was written in a site logbook. If the was an incident, the log book was the first thing ceased by authorities.

4X4 drawings show system interconnect were the norm. On training course you were given a blank schematic. By the end of the course you would have used up half your colour pencils making notation. Green for receive and red for transmit.

The lessons learned in those 18 years never left me. Every job I took after that, I carried a notebook. I typically start a project with what I call the "Napkin Drawing." The doodles sometimes on a napkin that flush out an idea. I find it really hard to discard the napkin even after the CAD's are done. Maybe I will miss something I had on the napkin. KiCAD'ing a schematic is time well invested. 

Up to this point only time has been invested. I have a scope of work, a component list and a way to estimate time. If at this point it never gets built, time can't be returned. I also discovered once mothballed it take time to recover the knowledge that got me to this point. The older I get, the harder it is to recover.

I find sharing project experiences on this site a great way to document.

I started my technology career in 1981. Entering a site required a sign-in and sign-out. Every action taken on the site or work on the equipment was written in a site logbook. If the was an incident, the log book was the first thing ceased by authorities.

4X4 drawings show system interconnect were the norm. On training course you were given a blank schematic. By the end of the course you would have used up half your colour pencils making notation. Green for receive and red for transmit.

The lessons learned in those 18 years never left me. Every job I took after that, I carried a notebook. I typically start a project with what I call the "Napkin Drawing." The doodles sometimes on a napkin that flush out an idea. I find it really hard to discard the napkin even after the CAD's are done. Maybe I will miss something I had on the napkin. KiCAD'ing a schematic is time well invested. 

Up to this point only time has been invested. I have a scope of work, a component list and a way to estimate time. If at this point it never gets built, time can't be returned. I also discovered once mothballed it take time to recover the knowledge that got me to this point. The older I get, the harder it is to recover.

I find sharing project experiences on this site a great way to document.