Caleb Sponheim Ph.D. is a User Experience Specialist with Nielsen Norman Group. A former computational neuroscientist, his expertise includes quantitative user experience research, statistics, analytics, and data science.
Plain-language definitions of the AI terms that come up in product and design work, from tokens and context windows to agents, evals, and prompt injection.
Pressure to adopt AI isn't evidence that a tool helps. The PROVE framework tests one tool against one task and produces a provisional decision you can defend.
An AI agent pursues a goal by iteratively taking actions, evaluating progress, and deciding next steps. Useful agents must be reliable, adaptive, and accurate.
Looking at and visualizing your raw, primary data is not a waste of time, quite the contrary. In fact, it can be the highest value action and the biggest return on investment that you can do.
To build good products, start by identifying the problem, not the solution. Especially with AI, if you start with a technology, delivering real value to your users and customers will be difficult.
