Putting AI into practice
AI makes researchers nervous, and that's fair: it can mislead us, and it makes it easier to find the answer we want instead of the one we need. So I build my own AI tools, test them against real people, and share what I learn with peers, because knowing when to step away from AI matters more than knowing how to use it.
UXR Claude skill
Open source
5
websites tested · 200+ reads · 15+ repo clones
Outcome
Open-source skill that the research community is reading and cloning.
I built a Claude skill to replace myself in conducting usability heuristic evaluations, then ran it across five websites to see what would hold up.
It turns out AI can do a lot. But it’s probabilistic. Early iterations confidently flagged problems that didn’t exist, especially against dynamic content the model couldn’t actually verify. So, the skill could generate some findings but it could not decide which findings were valid and worthwhile pursuing. That’s where the researcher’s work begins.
Read Part 1: Building the skill
Read Part 2: Five Websites, One Claude Skill, and the Thing Prompts Can’t Fix
Privacy and AI
We spoke to older adults across Canada about their needs and privacy expectations in remote healthcare technology. Unexpectedly, many had a lot to say about AI and the exciting (but sometimes scary) potential implications on future solutions.
Prototyping with AI
Designing and rapid prototyping an AI-enabled UX research repository that connects what researchers produce to what teams actually use when making product decisions.
Synthetic users: Fast, cheap, not human
Testing my portfolio site with 10 Claude-generated synthetic recruiter personas alongside 1 real participant to see whether AI can stand in for human usability testing.
Building AI Fluency
I am deepening my AI fluency through structured learning, including Anthropic’s AI Fluency Framework. I bring my lessons learned back to my teams to support their AI skills development.