What can AI-first thinking design, test and validate in 5 days?

When Jake Knapp wrote Sprint, building the prototype took a full day and a lot of ingenuity. Screens were stitched together using slides and held up by hope. It was a clever illusion, and it worked.

Today you can do infinitely more with the tools at hand, there's a huge shift in what's now possible. It also frees up time to focus on the most important areas; creating alignment, choosing the right focus and thorough testing with users.

Alignment comes first, and when the default plan is to design something for everyone, core design skills matter more than ever. On any key strategic project, I start with the people. That usually means meeting anyone who has differing views 1:1, to understand their hopes and fears. For this project, I started at the exec level. leadership had strong instincts, but it was essential to nail down all the open questions before using the sprint to provide a direction.

Before refining the scope, I ran 7 Ask the Expert interviews across leadership, marketing and our UK and French teams. The aim is simple: anyone with a view should be heard before we chose a key moment of focus. It also meant the final brief belonged to the company, not one person's idea of it.

Then I spoke to 5 clinicians across different specialisms for initial research. I stored everything we learnt from experts and users alike, in an AI knowledge base. This made it both quick and easy to call on the context gathered to making rapid, well informed decisions when building the solution.

The second was ideation. I ran Lightening Demos and Crazy 8s session with design, product marketing and engineering.

Using AI tools for ideation meant designers, and non-designers were able to get complex ideas and interfaces across in minutes. People often don’t feel confident sketching session and that’s followed by patient translation of ideas. The quality of what the group generated was high, and much of it shaped the final design.

Wednesday was build day, and it's where the gap with the old format was widest.

In a single day, using Lovable, I built a realistic end-to-end experience: sign-in, the core screens, and a full set of features.

Design is different now. We have so many modalities at our fingertips to maximise both inputs and outputs. The prototype used voice and image capture to make the experience truly seamless.

During testing clinicians were able to use something that listened and responded in a realistic way, leading to more accurate feedback and results.

AI can give you ten good answers in a few minutes, but it can't tell you which one the business needs most.