UX-Context Design: Using UX Knowledge to Inform AI-Generated Design - NN/G

Introducing NN/G Membership | Access all self-paced courses for $249 per year | Join by Jan. 26, 2027 |
Find the training option that fits your learning style.
July 24, 2026 2026-07-24
AI models produce output based on context. Context is everything the model can see when it does the work: your request, plus whatever instructions, standards, examples, and background information come along with it.
Context enables you to avoid middle-of-the-road output. For example, an AI model has been trained on a huge number of search screens, so when you ask for one, it produces an average search screen. It knows what software generally looks like. It doesn't know your users, your domain, your design standards, nor anything your team has learned from research. Unless that knowledge is in the context, the model designs without it.
Context leans a model’s output in a particular direction.
Think of a skilled builder designing your house without ever meeting your family. They design the average house. Two stories, because most houses have two stories. And if you use a wheelchair, or you have a baby who needs to sleep near you, or you have no kids and you and your partner both work from home, the design will be wrong in ways that impact day-to-day quality of life. That’s not the builder’s fault; the problem is the builder didn’t have context.
Similarly, the difference between generic AI output and AI output that fits your users and matches your organization’s standards is mostly a difference in context. So, what should we put in it?
Before answering, it helps to look at who is prompting these tools.
In many organizations, designers are no longer the only people producing designs. A product manager asks an AI tool for a quick mockup to make an idea concrete before a meeting. An engineer asks a coding assistant to add an export feature, and the assistant decides the button placement, the wording, the error states. These are all design decisions made by the AI.
Our live online course, AI for Design Workflows, helps designers identify meaningful AI tools and practices that will make your work more efficient.
The instinct might be to gatekeep who does design work, but that’s counterproductive. These tools are too available, too fast, and too useful for turning ideas into concrete forms. The more practical goal is to ensure that everything AI generates, no matter who prompts it, is informed by an organization's knowledge of its users and design standards.
That goal changes the output of research and design work. Historically, UX work produced deliverables for humans: personas, journey maps, research reports, annotated wireframes. A human read them, interpreted them, and made decisions. If AI is doing more of the building, then AI becomes the consumer of research and design deliverables.
And what an AI consumes is context.
Thus, the output of research and design work is, primarily, context that anyone in the organization can include when using AI to generate anything from slides to prototypes to working software. We call the creation of this output UX-context design.
UX-context design is the practice of discovering and curating what an organization knows and wants into the context that guides everything its AI tools generate: from who its users are and the world they live in, to how a product should look and behave.
UX-context design also involves testing the efficacy of that context with the models your team is using and refining the context to improve the output quality for everyone.
A first attempt at UX context might include what we already have: the personas, the journey maps, the findings reports. Some of those will help. But these artifacts were designed for human attention. A persona has a stock photo and a first name with the intention of helping a human to empathize and remember. However, a model does not need persuading, it needs the underlying reasoning.
That reasoning can be distilled with AI help. It can be useful, for example, to simply give raw research transcripts to a model and let it extract insights. Without human guidance, however, it’s possible that important takeaways may be lost in all the noise, or the AI may over-focus on the wrong takeaway.
To serve as maximally effective context, research and design output needs to be made “AI-ready” (or “machine-readable”), be curated by a skilled human, and made readily available to anyone that designs, no matter their role.
Let's look at a concrete example. In April 2026, Google Labs open-sourced DESIGN.md, a file format for describing a product's visual identity to AI coding tools. The format grew out of Stitch, Google's AI design tool, and is now a draft specification that anybody can use.
A DESIGN.md file lives alongside a product's code and holds two kinds of content. One part is “machine-readable” exact values: the colors, type sizes, spacing, and corner radii of the design system, written so tools can read them precisely. The other part is plain, human-readable prose explaining what those values are for and how to apply them, including do's and don'ts, providing guidelines for both humans and AI. Google's announcement says that, instead of guessing intent, AI tools can "know exactly what a color is for," and can check their color choices against accessibility contrast standards.
This serves as a good example of a successful format for UX context, and provides some lessons. It's a text file, kept next to the code, that AI tools read every time they generate something. Unlike traditional deliverables, there is no handoff: UX context feeds directly into product creation.
But visual identity is only one part of user experience and product design. What about everything else from research and design that informs the building of a product?
Let's imagine another text file, with a broader intent than DESIGN.md. We'll call it UX.md. It would reference DESIGN.md for visual standards and point to where the product's actual components live in the code. How