Human-in-the-Loop Is Not a UX Pattern
As organisations adopt AI systems for increasingly complex work, “human-in-the-loop” has become the default answer to co…
Designing Agent Interfaces for High-Stakes Decisions
AI systems are increasingly moving beyond summarisation and copilots into something more consequential: decision support…
Agentic Interfaces: Beyond the Chat Window
For the last few years, AI product design has largely revolved around one thing: the chat interface. Prompt in, response…
AI and ML Design Resources for UX Designers
I’ve come across a few really good resources for UX Designers getting into or involved in designing for complex apps and…
A Practical Introduction to AI Agents
How they work, why they matter, and what you should know before building one AI agents are quickly becoming one of the m…
Adaptive Learning for AI Agents
As AI agents become more autonomous and take on increasingly complex tasks, adaptive learning becomes a core requirement…
Designing Agents
I’ve recently been working on an agentic fraud alert review system for a bank, where our agent monitors transaction aler…
Good Models Die in Notebooks
In large consulting projects and enterprise AI programs, too many AI and data science projects follow the same unhelpful…
Thumbs Up to the Humans in the Loop
Back in the early days of building apps, when we were still deploying things with FTP and debugging with alert(), one of…
Thinking beyond chat interfaces for human-agent interaction
From Chat to Click Chat-based interfaces are the go-to solution for agent interactions, helping new users of agent syste…
How do you design explainability in Complex Systems?
AI has become a driving force in software from personalised recommendations to critical decisions in healthcare and fina…
Avoiding AI Gimmicks: Designing for Real User Needs
I’m going to start with a Steve Jobs clip. In it, he says “you’ve got to start with the customer experience and work bac…
Designing for Trust in AI Applications
I’ve been looking into how we can make user perceptions of AI systems more positive when it comes to trust. This is part…
The Power of Narrow Inputs and Outputs for Language Models
Yes this is about generative AI. Large language models (LLMs) have become versatile tools capable of handling tasks rang…
Rethinking: Are LLM chat interfaces really what users want for search?
Why are LLM chat interfaces being used to display search results? With the rise of AI-powered tools, many apps are now u…
