LLMs (I use ChatGPT) can take a generic process description, spit out the result in mermaid, which can then be imported and refined in something like draw.io. Yes, you’ll have to correct a few things by hand, but it drastically speeds things up. Last time I check draw.io is supported in obsidian.
I recently tried this, but the import to draw.io did not go well. It imported as a single static image rather an editable diagram. Maybe I did something wrong?
Usually in such cases either copy and paste the error message from draw.io, or screenshot it and upload to chatGPT. It will debug it for you.
There’s also a specific sequence of steps to import mermaid scripts, I don’t remember the menu location by heart, ChatGPT can also give you the steps needed to do this.
