Mobile Menu Button
AI Design Sprint

From AI ideas to
real product opportunities.
In one day.

Whether you're exploring where AI could make a difference or deciding which ideas are worth pursuing, our AI Design Sprint helps your team find clarity, build tangible prototypes and define what comes next.

Recent Sprints With:

Starting Points

You see the potential. But where do you start?

Explore how AI could create meaningful value for your customers, products or processes. Identify promising opportunities and turn the strongest ideas into something tangible.

You have plenty of ideas. But which ones are worth pursuing?

Challenge assumptions, prioritize opportunities and rapidly prototype promising concepts to make better informed product decisions.

The Challenge

Your problem isn’t the ideas.

The pressure is real and the starting point isn’t obvious. Everyone agrees AI matters. Nobody agrees on where it matters for you. So the question goes into workshops, task forces and strategy decks, and comes back out as a longer list of possibilities. People start experimenting on their own. Six months in, everyone is busy and nobody can say what it adds up to.

Your competitor has access to the same efficiency.

Most AI programs point inward: summarize the meeting, draft the email, clean up the spreadsheet. Useful, and it makes the quarter look better. But the question is: what does AI do to the thing you actually sell? Does your product get more valuable? More capable? Harder to replace? Every competitor has access to the same efficiency. The product is the part that’s yours.

The Sprint

The AI Design Sprint brings the people who know your product and your customers together for one day, to find where AI adds the most and to build it.

The AI Design Sprint combines zigzag’s experience in product strategy, human-centered design, and technology with a research-backed approach to AI innovation. Our methodology has been developed and refined through real-world projects and academic collaboration, including research published at the 2026 ACM Designing Interactive Systems Conference in collaboration with Carnegie Mellon researchers.

A Problem Worth Solving

The point in your user journey where the pain or upside is greatest, identified and agreed on by the people who’ll live with it.

A Ranked Backlog of Ideas

Every idea your team generated, captured and ranked against the problem, so the ones you don’t build today aren’t lost.

Working Prototypes You Can Try

Real code that runs in your browser, built inside your own design system so it looks like your product from the first screen.

A Decision, Not a Follow-Up

Results are synthesized as the day runs, so next steps get agreed while everyone’s still in the room, not over email weeks later.

A Case for Your Leadership Team

Continuing usually needs a budget decision. A working prototype and the reasoning behind it make a different conversation than a slide deck.

Testimonials

“We knew we had to start somewhere, and this format helped us identify the topics with the most potential for the least effort.”

Simon Drees

Director of IT, HAUBER

The Day

The workshop itself is one day. How much goes into it beforehand depends on your topic and how well we already know each other.

Before the sprint, we turn the material you share into a private knowledge base for ziggie, our own local and secure AI, and set up a prototype scaffold from your design system. That usually takes a few days, mostly on our side. If we’ve worked together before, much of it is already in place. It’s what lets the day itself move from problem to prototype.

1

Morning

You mark where it hurts.

Your team walks through the user journey it lives with every day and marks the points that cost the most time, money or patience.

2

Midday

You see what AI can do right now.

A working session on current capabilities, hands on the material. By the end of it everyone in the room shares the same picture of what’s realistic.

3

Early afternoon

You come up with ideas and pick one.

Everyone generates against that problem, the ideas get shared and ranked, and the team agrees on what’s worth building the same day.

4

Afternoon

You build it and look at it.

We build it in code with you and it runs in your browser. Then you try it, break it, and decide what should happen next.

5

Evening

We close with what everyone takes away.

Next steps get decided on the spot, while the day’s momentum is still in the room.

Why It Works

AI takes on the slow parts: research, synthesis, and building. That leaves your team the whole day for the decisions only people can make.

Design sprints have been around for more than a decade, and the format works. What used to slow it down was everything around the workshop: getting up to speed, making sense of the output, and turning ideas into something you can try. Here’s how we handle each of those.
<text>We arrive knowing <secondary>your domain</secondary>, so no one spends the morning explaining it.</text>

We arrive knowing your domain, so no one spends the morning explaining it.

Before the workshop, we build a private knowledge base from your material: project documentation, call transcripts, past presentations, and a glossary for your terminology. We test it until its answers come back grounded in the right documents. On the day, the room starts from your context instead of a briefing.
<text>Our own local AI, <secondary>ziggie</secondary>, checks the room’s work against what your business already knows.</text>

Our own local AI, ziggie, checks the room’s work against what your business already knows.

ziggie is connected to the workshop board. It reads what the room produces as it happens and queries it against the knowledge base. Pain points get checked against what people said in past interviews, and ideas get compared to what’s been tried before. The synthesis happens during the workshop, not in the weeks after.
<text>We bring the method and the tools. The expertise in the room is <secondary>yours.</secondary></text>

We bring the method and the tools. The expertise in the room is yours.

We facilitate, handle the tooling, and make sure the day produces something. What your users need, where the constraints sit, and what the business can actually absorb come from your people. AI speeds up the work around those calls but doesn’t make them, and it’s the one part nobody can prepare in advance.
<text>Prototypes built in <secondary>your design language,</secondary> not the model’s default look.</text>

Prototypes built in your design language, not the model’s default look.

We build and maintain design systems for a living, and we work on how AI tooling behaves inside them. Before your sprint, we set up a scaffold from your design tokens and components, so every prototype starts inside your visual language. The result is something your leadership recognizes as their own product.

Data Security

ziggie, our own local AI, works with your material on our hardware, so it never has to leave our office. Only the prompts for building prototypes go out, and ziggie filters those first.

What Stays with Us

Your documentation, transcripts and project knowledge. They go into our own local AI model, on hardware we own, in our own office. Nothing of it is sent to any external AI service at any time. Our office and servers are TISAX-assessed.

What Leaves, and How

Prompts for building the prototypes. We use a commercial coding model for this, because no local model matches it yet. Every prompt passes through our local assistant first, which removes customer names, part numbers and pricing. The model sees the shape of the problem, not your business. If your organization hasn’t cleared AI coding tools, that doesn’t stop the day — we work on our machines and our licences.

The Setup

Who Should Be In the Room

Around eight people works well. The mix matters more than the count: people who know your customers, people who know your systems, and someone senior enough to act on the outcome.

No AI Experience Needed

Some teams arrive having barely touched AI, others already have people building with it. The day starts from your problems, not from the technology, so both work.

On-Site or Across Time Zones

Your office, ours in Berlin or Stuttgart, or remote. We’ve run it across four locations and two continents at once, with remote participants building alongside everyone else.

Share What You Can

Documentation, past project files, recordings of customer calls, and access to your design tokens and components. The more you share, the more the day starts from your context. If it can’t leave your building, we work without it.

Timing Is Flexible

The date follows your team’s calendar. Once the group is confirmed and your material is in, we plan the preparation around it.

Price Depends on Scope

Every sprint is scoped to your topic and material. Tell us what you have in mind and we’ll come back with a figure.

The Team

Experienced product thinkers, designers and technologists. Working as one team.

Every AI Design Sprint is led by an interdisciplinary team from zigzag, combining expertise in product strategy, user research, UX/UI design, AI and software engineering.
With more than a decade of experience designing and building complex digital products for international clients, we know how to turn ambitious ideas into solutions that work in the real world.

We assemble the right team for each sprint, bringing together people who understand your industry, can challenge assumptions, identify meaningful opportunities and turn ideas into tangible prototypes. You bring the knowledge of your business and customers. We bring the outside perspective, the methodology and the expertise to help move things forward.
Andreas Haas

Andreas Haas

Business Development & Strategy Director

Saurabh Datta

Saurabh Datta

Principal Designer

Mai Luong

Mai Luong

Senior Designer

Dennis Knopf

Dennis Knopf

Director Project & Product Management

FAQ

Short answers to the practical questions, from who the sprint is for to who owns what comes out of it.

The sections above go into more detail on each of these. If your question isn’t covered here, or depends on your specific setup, send it to us and we’ll answer it directly. That includes questions from your legal or compliance team.