"Using a pre-built template strategy: The Atlassian team realized that AI was often messing up core elements and not completely understanding complex commands. So they created a sort of "design system" for their AI led prototyping. Here they feed a page with pre-coded elements which AI doesn't change, but lets the tool work on other elements which are open to interpretation in a way."
"They built instruction files: Unlike most designers who just ask AI tools to code in a certain programming language or use a certain framework, their team has created certain instruction files to "guide the AI". This instructions file (essentially a text file) might have a specific instruction to use a design system element, variable or certain token in case the AI encounters a certain type of element."
Top companies including Meta and Atlassian build AI workflows and invest millions to train employees on them. Atlassian applies an AI-powered design-to-prototype workflow to accelerate design and testing at scale for enterprise software. The team uses a pre-built template strategy that feeds pages with pre-coded elements the AI must not change, allowing the tool to modify other elements. They create instruction files—text files that guide the AI to use specific design system elements, variables, or tokens when encountering particular elements. The team pairs frameworks like Tailwind with override instructions so the AI uses internal components in designated areas, balancing automation and control.
Read at Medium
Unable to calculate read time
Collection
[
|
...
]