A civil service exam prep portal adjusts practice-question difficulty from each applicant’s prior answers. Which education AI concept is that?

A civil service exam prep portal that adjusts practice-question difficulty from each applicant’s prior answers applies adaptive learning that personalizes practice difficulty based on learner performance. Adaptive engines raise or lower challenge to keep practice productive, which is a core education AI pattern usable for municipal exam preparation. The portal supports practice; it does not replace the official civil-service exam administration rules or scoring authorities.

Mastery tracking that personalizes practice difficulty using threshold advancement rules advances topics after proficiency thresholds are met rather than continuously tuning item difficulty in response to each answer, so it misses the adaptive concept in the stem. Learning analytics that personalizes practice difficulty from cohort performance models draws on cohort-level models rather than tuning difficulty from each applicant's own prior answers, so it serves aggregate analysis rather than individual adaptation. Automated scoring that personalizes practice difficulty using essay rubric outcomes evaluates essay responses against rubric criteria rather than adjusting practice-question difficulty from each answer, so it grades writing rather than driving adaptive practice.

Exam caveat: Adaptive learning is performance-based difficulty adjustment. Mastery tracking via threshold advancement rules, analytics from cohort performance models, and scoring from essay rubric outcomes are standard distractors.

Operational check: Separate practice adaptation from the official exam item bank, monitor for bias across applicant groups, disclose that practice difficulty is personalized, and keep human review of item quality and fairness in the prep catalog.