FR 2025: AI-Powered UX

Working with AI: What UX practitioners need to know about AI as a research tool

Thanks for joining me at AI-Powered UX!

Download the handout and slides
Sign up to get notified about office hours and workshops.

References from the talk

Andon Labs. (2025, September 8). Vending-Bench: Testing long-term coherence in agents. https://andonlabs.com/evals/vending-bench
Charlotin, D. (2025). AI hallucination cases database. Damien Charlotin. https://www.damiencharlotin.com/hallucinations/
Hewing, M., & Leinhos, V. (2024, December 6). The Prompt Canvas: A literature-based practitioner guide for creating effective prompts in large language models. arXiv. https://arxiv.org/abs/2412.05127
Laban, P., Hayashi, H., Zhou, Y., & Neville, J. (2025, May). LLMs get lost in multi-turn conversation. Microsoft Research. https://arxiv.org/abs/2505.06120
Microsoft. (2025, January 22). RAG chunking phase. Microsoft Ignite. https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-chunking-phase
Morgan, T. M. (2025, February 13). Declaration of T. Michael Morgan in response to order to show cause, Wadsworth v. Walmart, No. 2:23-CV-118-KHR (D. Wyo. 2025). https://cdn.arstechnica.net/wp-content/uploads/2025/02/Wadsworth-v-Walmart-Declaration-2-13-25.pdf
OpenAI. (2025, September 5). Why language models hallucinate. https://openai.com/index/why-language-models-hallucinate/
Paine, L. (2025). AI for UX researchers [Workshop]. Rosenfeld Media. https://rosenfeldmedia.com/rosenfeld-workshops/workshop/ai-for-ux-researchers/
Paine, L. (2025, Fall). What can we learn from running qualitative analysis 108 times on an LLM? [White paper]. https://llewynpaine.consulting/report-108-runs-of-llms-for-qualitative-analysis
Rosenfeld Media. (2025, June 10-11). Designing with AI 2025 [Conference]. Online. https://rosenfeldmedia.com/designing-with-ai/
Singer, N. (2023, May 27). Here’s what happens when your lawyer uses ChatGPT. The New York Times. https://www.nytimes.com/2023/05/27/nyregion/avianca-airline-lawsuit-chatgpt.html
Willison, S. (2025, May 25). Highlights from the Claude 4 system prompt. Simon Willison’s Weblog. https://simonwillison.net/2025/May/25/claude-4-system-prompt/
Zamfirescu-Pereira, J. D., Wong, R. Y., Hartmann, B., and Yang, Q. (2023, April 19). Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 437, 1–21. https://dl.acm.org/doi/10.1145/3544548.3581388