Designing Human-AI Experiences

Six load-bearing principles. One full day. Your product on the table.

For over twenty years, I have been designing at the intersection of human behavior and emerging technology. The hardest design problem of this decade is not how to use AI tools — it is how to ship AI products that people understand, trust, and choose to come back to. The field has been quietly converging on the answer for years; most teams just have not had the time to read it all.

That is what this workshop is for.

Across one full day in Berlin, you learn the 6 HAX Principles — Empathy First, Automation vs. Augmentation, Transparency and Confidence, Real Control and Editability, Graceful Failure, and Mental Model Shaping — and apply each one to a real product you ship or use weekly. The principles are not invented from thin air; they are researched, synthesized, and curated from the canonical work at Microsoft, Google, Apple, GitHub, the Shape of AI catalogue, AIverse.design, and the academic literature on human-AI interaction — pressure-tested across international  fieldwork at Optimizer in Pharma, Healthcare, Finance, Logistics, and the public sector.

We use the 7 Sins of AI Product Design as the diagnostic lens, the 6 HAX Principles as the antidote, and the AX (Agentic Experience) Framework as the strategic scaffold for shipping AI behavior — not just AI interfaces. Hands-on. Group work. A working prototype by the end of the day.

You leave with three concrete artifacts: an audit of a real product, a HAX-principle redesign brief, and a functional prototype that takes the unhappy paths seriously — graceful failure, uncertainty signaling, real human agency.

For senior UX designers, product managers, design leads, and engineers shipping AI features. No machine-learning background required.

What you'll learn

‍
The 6 HAX Principles, applied. Empathy First. Automation vs. Augmentation. Transparency and Confidence. Real Control and Editability. Graceful Failure. Mental Model Shaping. The six load-bearing beams of every AI product worth coming back to — applied, in the room, to a product you actually ship.

HAX Design Patterns. The practical patterns that make the principles concrete — explainability cues, calibrated trust signals, feedback loops that compound, error handling that does not insult the user, and editability as a first-class design problem.

The AX Framework. A strategic lens for assessing decision boundaries, responsibility, and trust. We use it to align People, Machines, and Intelligence around a real product problem — and to surface what happens behind the interface, not just on top of it.

Human-Centered AI Integration. Translate user needs into data and decision strategies. Set automation limits deliberately. Mitigate bias before it ships. Define the AX Metrics you will actually monitor post-launch — because shipping an AI feature is not the end of the design work, it is the beginning of it.

‍

Workshop schedule — 09:00 to 16:00 (including breaks)

‍
09:00 – 10:15 · Module 1 — The AI Experience Regression

We open with a Confessional Audit. Using the 7 Deadly Sins of AI Product Design as the frame, we shift from analyzing digital façades — the UI — to auditing system behavior. We apply the AX Human Layers lens to unpack intent, decisions, and the trust assumptions products quietly inherit.

10:15 – 10:30 · Coffee Break

Morning refreshments and networking.

10:30 – 12:00 · Module 2 — The Antidotes: Core HAX Principles

We work through the balance between Automation and Augmentation, then design for explainability and calibrated trust using indicators over raw data. We apply the AX Autonomy & Control Check to "Gold Standard" products to assess what real user control and meaningful fallback limits look like in production.

12:00 – 12:45 · Lunch Break

Sponsored networking lunch at a nearby restaurant.

12:45 – 14:15 · Module 3 — Strategy & Framing: The Tri-Canvas

Hands-on group work with the AX Sprint Canvas. We align People, Machines, and Intelligence to solve a real problem. Then we shift to use-case validation and data strategy, using the 7 AX Pillars as guardrails for ethical, functional decisions.

14:15 – 14:30 · Afternoon Break

Quick refreshments before the final sprint.

14:30 – 15:30 · Module 4 — Rapid Prototyping: The "Devigner" Phase

Build a functional prototype where the AI's behavior is the product. Using tools like Figma AI, V0, or Lovable, we focus on the Unhappy Paths — graceful failures, uncertainty signaling, and preserving human agency when the model gets it wrong.

15:30 – 16:00 · Final Pitch & Wrap-up

Each group presents the underwater logic of their solution. Not just screens — the data sources, the bias mitigation plans, and the AX Metrics they would monitor post-launch. We close with what you take back to Monday morning.

‍

‍

‍