Every student learns differently. pref0 captures learning style preferences, explanation depth, and pace so tutoring agents personalize instruction automatically.
Real corrections pref0 extracts and compounds across conversations.
"Show me an example first, then explain the theory"
learning_style: examples_first0.70"Use analogies, they help me understand"
explanation_style: analogies0.70"Slow down, one concept at a time"
pace: slow_methodical0.70"Quiz me after each section"
assessment: frequent_quizzes0.40"Use code examples, not pseudocode"
example_format: real_code0.70"I learn better with visual diagrams"
content_format: visual_diagrams0.40Explain recursion to me
Recursion is a programming technique where a function calls itself. The key components are a base case and a recursive case...
Can you show me a concrete example first? I understand better when I see code.
pref0 extracts the correction from this conversation and adds it to the user's preference profile. Next time, the agent gets it right.
Some students prefer examples first, others prefer theory. The tutor adapts to each learner.
pref0 learns whether to go fast or slow, detailed or high-level for each student.
The tutor remembers learning preferences from previous sessions. No re-calibration needed.
As confidence compounds, the tutor can adjust its approach based on demonstrated learning patterns.
Your users are already teaching your agent what they want. pref0 makes sure the lesson sticks.