Generative UI in Native Apps

Are you a final-year master’s student looking for a thesis project that blends real-world impact with cutting-edge tech?

At Framna, we are passionate about creating digital products that shape markets and make everyday life better - and we want you to be part of it.

Every year, we welcome a group of master’s students into our Stockholm studio to spend their final semester with us. You will sit alongside our developers, designers, testers, analysts, and product delivery leads, get a place to sit in our cozy office, and join our social and learning activities - from lunch-and-learns to our weekly Friday demos and AWs. It is a chance to do your thesis in a collaborative setting, surrounded by people who are happy to share what they know.

Background

Generative UI is when a large language model assembles an app's interface at runtime, rather than a developer hardcoding it. As apps take on more open-ended requests, a fixed set of screens covers less of what users ask for. Protocols for letting a model decide what to render are starting to emerge.

But giving a model control over what gets rendered raises hard questions: how much freedom the model should have, what happens when its output is invalid, inconsistent, or misleading, and what the approach costs in latency, reliability, and safety.

In this thesis project, you will implement the same native app feature under several different model-to-interface contracts, ranging from tightly constrained to fully generative, and empirically compare how each performs across dimensions that matter in real products.

What you will do

Some potential tasks within this thesis include:

• Implementing a native app feature under three types of model-to-interface contracts

• Evaluating each approach on schema validity rate, component appropriateness, consistency across repeated requests, and latency to first render

• Measuring token cost per rendered screen and assessing design system conformance and visual drift

• Identifying failure modes and testing graceful degradation when model output is invalid

• Investigating safety risks, including whether generated interfaces can be steered toward misleading or harmful outputs

• Producing a taxonomy of failure modes and architectural guidance for where on the constrained-to-open spectrum a given feature belongs

Who you are

This thesis may suit you if you:

• Are interested in mobile development, design systems, or AI systems

• Are curious about the architectural and product implications of AI-generated interfaces

• Enjoy building prototypes and designing structured empirical comparisons

• Plan to start your master's thesis project in January 2027

• Have the opportunity to work from our Stockholm studio

About Framna

Framna means ‘to bring forward’ in Old Norse. And that is exactly what we do. We partner with industry leaders (and those about to be) to create excellent digital products that define markets, reshape industries, and deliver meaningful impact.

Born from the union of digital agencies Bontouch, Move, and Shape, Framna emerged from a strong, product-led culture. Today, over 600 of us collaborate across ten studios in Denmark, the Netherlands, Poland, Sweden, Switzerland, and the US.

Every day, millions of users around the world rely on the products we help shape. From seamless payments to daily commutes, from better health management to smarter shopping. Our work supports more than €150 million in daily transactions and consistently earns an average App Store rating of 4.5.

Together with some of the world’s most ambitious brands, including Essity, SJ, Swish, and SEB, we craft products that lead markets and push boundaries. Because when products win, businesses win. We call it Win by product.

Our hiring process

• Psychometric assessment - personality and logic test

• Interview with our recruiter

• Case assignment

• Case interview