I’ve had some interesting results using GPT4 to generate mermaid diagrams from descriptions of my architecture or processes.
Plus, the output being code, it’s easy to fine tune when the inevitable mistake creeps in every once in a while.
It’s funny. I have never documented anything so thoroughly. It was just too time-consuming. Now I do. In part because I know there will be a diagram to complement it and improve the likelihood any of it will prove useful to someone at some point.
But also because keeping said documentation and diagrams up to date will be easier.
I've been using ChatGPT to generate PlantUML diagrams with great success. If the diagram doesn't look right, it means I haven't been able to describe the solution well enough in the prompt. Repeating the description in the prompt until I get it right means that I can can practice explaining the solution in a way that helps me describe the solution to humans too.
> I can can practice explaining the solution in a way that helps me describe the solution to humans too.
That too. Also had some interesting results asking it to rephrase, structure and improve whatever description I’ve written for the process I’m documenting.
Especially when my description felt more like some rambling than some clear and precise unambiguous explanation.
Also a great way to generate, and more importantly keep up to date, short and concise overviews, for both technical and non-technical stakeholders.
Plus, the output being code, it’s easy to fine tune when the inevitable mistake creeps in every once in a while.
It’s funny. I have never documented anything so thoroughly. It was just too time-consuming. Now I do. In part because I know there will be a diagram to complement it and improve the likelihood any of it will prove useful to someone at some point.
But also because keeping said documentation and diagrams up to date will be easier.