Category: Field Note
Brief essays and conceptual sketches that don’t fit elsewhere. Often unfinished, always interpretive — these pieces hold tension, surface contradiction, and offer a space to think around the edges of UX practice.
-
Who’s listening? The two audiences of AI conversations
In AI-mediated service, people speak to one listener and are read by another. What changes for disclosure, trust, accessibility and interface design.
-
The abstraction debt: what happens to the time AI gives back?
AI can make an organisation look more capable while the experience behind that capability drains away. On judgement, learning, and what leaves with the employee.
-
Dropped Ideas: Working Frameworks
I built five working frameworks, then removed them. This is the record of why. The idea was reasonable. I had a set of half-formed instincts about research practice, and I thought that naming them — turning each into a small three-move framework — would sharpen them into something teachable and distinct. Working with an LLM…
-
How Do You Ask a Chameleon to Stop Changing Colour
There are three studies open on my screen. Interviews from a discovery sprint, behavioural data from Contentsquare, a usability session from six weeks earlier. I have read all of them. Not skimmed — read, the way you read something when you know you will need to find the gap between what participants said and what…
-
Agentic AI Reading Instrument
This experiment helps inspect short ideas about agentic AI through fixed critical lenses. Rather than simulating an assistant, it reads where delegation compresses context, assumes capability, and leaves hidden recovery work behind. The Lasagna Dilemma works through the same problem on one shopping request.
-
The Lasagna Dilemma: Good Enough, Context Loss, and the Future of Agentic Commerce
Why “order everything for a lasagna dinner for four” exposes the limits of agentic commerce: compressed intent, context loss, liability, and what brands still control.
-
The agent can order the tomatoes. It just can’t know why you won’t eat them in December.
AI agents can reproduce our purchases without reaching our needs. On the embodiment gap: unstated constraints, three layers of preference, and how an agent might learn.
-
EU Consumer Law and UX: The Consumer as Ecosystem
The law requires withdrawal to be as easy as purchase. The footer link fails this test on every dimension. The withdrawal button is a legal actor. When absent, the right cannot be exercised. When present with a deadline counter, it performs the law’s symmetry requirement on behalf of the consumer, making the safe action the…
-
Rethinking Users as Ecosystems: My take
The central tension Youngblood and Chesluk’s framework exposes here is that holding the phone is not irrational from within the ecosystem — it’s the path of least resistance, it enacts social intimacy, and the body’s motor habit reinforces it.
-
Interpreting Intent: When Agents Decide for Users
In planning meetings, it now comes up almost casually. Someone reports that a task is done, the agent took care of it, and the conversation moves on. Later, when the decision is questioned, there is a pause. No one remembers why that option was chosen. There is no error to point to, no rule that…