Sunwise.
Making UV information personal and understandable.
View project Adrian built Sunwise to make sun-exposure information easier to understand, and to put Martini’s AI-assisted development workflow into practice in a live product.
The challenge
A weather forecast does not explain what UV exposure means for an individual. The product challenge was to make that information approachable without presenting an estimate as a promise of safety.
The approach
Sunwise gives people a short path from a skin check to relevant UV information. It is also a working example of how we use in-house agent prompts and memories to move from a product idea into production, while keeping the purpose of the experience in view.
A focused first use
The core check combines a photo-based skin-type estimate with local UV conditions and forecasts. It can be used without creating an account, with location access requested from the user.
Privacy & clear limits
The site states that photos are analysed in memory and discarded. Results are educational estimates, not medical advice or guaranteed safe exposure times. That distinction is part of the product experience.
Beyond the check
Supporting guides explain skin types, UV and sun protection, while city pages make local UV information easier to find. The experience starts with Australian sun awareness and supports locations worldwide.
OUR APPS.
OUR PRACTICE.
Sunwise gives our workflow a clear design constraint: make the experience simple while preserving the limits of what it can tell someone. Speed in development is useful only if the product’s wording and behaviour stay aligned with that purpose.
Across these apps, our in-house prompts give agents direction and our memories carry useful context forward. We use our own products to refine that approach, with the aim of developing production applications quickly and precisely.
- 01 / DIRECTION
Give the work a clear brief.
Start with the problem and the intended behaviour. A focused prompt gives an agent something concrete to work towards.
- 02 / CONTEXT
Carry the learning forward.
Agent memories keep useful context available between iterations, so each task can build on the thinking that came before.
- 03 / APPLICATION
Bring the workflow to your business.
Apply the same approach to a new product or an existing process. Production quality remains a design and engineering responsibility.
THE WORK,
UP CLOSE.
- 01Photo-based skin-type estimation
- 02Local UV conditions and forecasts
- 03A core check without account creation
- 04Educational guidance and city UV pages
- 05A live product for refining our agent workflow
An approachable educational app, and a practical setting for refining how we turn a focused brief into a production experience. The lesson for other businesses: define what a product should do, and its limits, before accelerating the build.
BUILT BY ADRIAN CIASCHETTI. COVER: SCREENSHOT OF THE PUBLIC HOMEPAGE.