I recently designed ORYN — an AI-native workspace built around intent, context, and controlled autonomy.
The challenge wasn't simply designing an AI interface. It was figuring out how much of the interface should exist before the user expresses an intent — and how much AI should be trusted to do on its own.
Throughout the case study, I explored multiple directions rather than jumping directly to the final UI: chat-first interaction, contextual AI, generative interfaces, and different autonomy models.
That exploration led to two principles that shaped the final experience:
The interface should follow the intent.
and
Don’t automate the decision. Automate everything around it.
The final concept uses risk-based autonomy, ORYN can gather context, prepare information, structure workflows, and recommend actions, while consequential decisions remain with the user.
A project focused not just on what AI can do, but on how an AI product should behave.
I recently designed ORYN — an AI-native workspace built around intent, context, and controlled autonomy.
The challenge wasn't simply designing an AI interfac...