In a practice space, students practice for a test on their own, with questions the AI writes from your source materials. It picks each student's next question based on how they're doing per topic, brings topics back over time, and gives personal feedback on every answer. You follow everyone's progress on the Insights tab.
Students see their progress on each topic in the space, so they know what to work on next. To set one up, see Setting up your first practice space.
How practice spaces work
Practice topics
Practice spaces are built around the source materials you add and a set of topics. Examplary drafts the topics from your materials, and you can review and adjust them under Mastery topics. Every question is about one of these topics, and students see their progress per topic.
Infinite practice canvas
New questions are generated in the background while students use the practice space. Based on the student's answers, the space picks the most useful next questions to show them.
This works much like your queue on Spotify or Apple Music: as the student works on questions, the AI adds questions to their queue that are relevant for them, based on how they did on each topic and on a few core learning principles.
At the start, the space gives priority to topics where the student hasn't answered two questions yet, so the AI can form a baseline of how well they understand each one.
Questions at different levels
Every question gets a difficulty level, from baseline to expert, and a level from the taxonomy (Bloom's, unless you chose another one). When the AI picks the next questions, it sees those levels next to the student's results per topic.
Spaced repetition and interweaving
Once a baseline is formed, the space focuses on the topics the student needs the most help with, and mixes in questions about the topics they already understand well.
It also applies spaced repetition: a topic the student hasn't seen in a while comes back, to help them remember it in the long term.
Personal feedback
Students get personal feedback from the AI after each question they answer. By default, it follows this structure:
- What was wrong
- Why it was wrong
- What could be done to improve it
You can change how the AI writes this feedback with your own instructions, see Providing feedback instructions.
After they answer, Examplary also updates the overall and per-topic feedback for the student. It focuses on what they do well, and which topics and principles still need their attention, so they know how to keep studying towards their goal.
Quality and safety
Ensuring high-quality questions
Questions generated in a practice space are always grounded in the source materials you add to the space. That makes made-up facts less likely, and makes sure the questions use the terminology the student has read before and heard in the classroom.
Each generated question is also scored automatically against about thirty research-based principles for good test questions. These include things like:
- Whether the question tests a single concept
- Whether the question stem is a direct question or a complete statement
- Whether the question language avoids unfairly disadvantaging particular groups
Questions with low scores are far less likely to be shown to students. You can also Upvote or Downvote a question yourself under Example questions, which moves it up or down the list.
Teacher insights
You can see student progress in the practice space at any time, on the Insights tab. It shows how the class is doing as a whole and how each student is doing, including every question a student answered, their answer and the feedback they were shown. Following student progress in a practice space walks through it.
Reporting mistakes and invalid content
Students can report incorrect or harmful AI-generated content with Report AI response, in the menu next to a question or its feedback. Teachers find the same option next to each answer in a test's results.
A report sends the Examplary team the question, the answer and what the AI did with it, together with the note you write. This helps our team keep improving practice spaces.
Practice spaces are how Examplary does AI practice questions: practice for students, with you in charge of the materials, the topics and the instructions.