Build the next realistic practice set for each learner
Build a dynamic exercise set from difficulty-labelled tasks. SubSchool uses the learner’s subject-level success by difficulty to choose and persist one set for that lesson.
Static or dynamic set
Each step stays editable, visible, and connected
These product views use example data to show what the teacher actually sees—not an abstract feature diagram.
- Step 01
Subject success by difficulty
A static set keeps teacher-defined item order. A dynamic set selects from an exercise pool labelled with A/B/C/D difficulty.
sourceSubject success by difficulty
DescriptionBook or PDFVideos＋Add approved source materialPDF, DOCX, video or lesson recording - Step 02
Static or dynamic set
For dynamic delivery, the selector reads stored learner success percentages by difficulty for the course subject. Strong success keeps or moves the recipe toward more advanced tasks; weaker results at a higher level can move it back to simpler practice.
courseStatic or dynamic set
AI & PRODUCTDecision-making with evidenceModule 1Frame the decision3 lessons Module 2Collect useful evidence4 lessons Module 3Test the recommendation3 lessons - Step 03
Volume recipe
The requested volume determines how many exercises are needed at each difficulty; shortages are filled from the remaining pool.
practiceVolume recipe
Lesson contextInterview evidence and decision risks01 Explain your recommendationExtended answer · 10 pointsIncluded02 Prioritise the evidence gapsScenario · 8 pointsIncluded03 Record a two-minute defenceSpoken response · 12 pointsReview - Step 04
Deterministic selection
The selected exercise IDs are saved for that learner, lesson, and set so later visits return the same selection.
responseDeterministic selection
AssignmentDefend the decision and name the largest uncertainty.▶02:14Student response“The strongest evidence supports option B, but the sample is still too narrow…”
Transcript ready - Step 05
Persisted exercise IDs
Build an editable exercise pool from the actual lesson context, then select the tasks, response formats, difficulty, and points that fit this learner.
practicePersisted exercise IDs
Lesson contextInterview evidence and decision risks01 Explain your recommendationExtended answer · 10 pointsIncluded02 Prioritise the evidence gapsScenario · 8 pointsIncluded03 Record a two-minute defenceSpoken response · 12 pointsReview
Choose a static or dynamic set
A static set keeps teacher-defined item order. A dynamic set selects from an exercise pool labelled with A/B/C/D difficulty.
Move up after success and simplify after difficulty
For dynamic delivery, the selector reads stored learner success percentages by difficulty for the course subject. Strong success keeps or moves the recipe toward more advanced tasks; weaker results at a higher level can move it back to simpler practice.
Respect the configured volume and available pool
The requested volume determines how many exercises are needed at each difficulty; shortages are filled from the remaining pool.
Persist one selection for the lesson
The selected exercise IDs are saved for that learner, lesson, and set so later visits return the same selection.
Keep the boundary explicit
The released selector does not diagnose named knowledge gaps or error types. It also does not use recency, teacher-priority rules, locked required tasks, or a learner-facing explanation.
Current dynamic-set selection
The released selector uses the course subject, stored success percentages by difficulty, the requested volume, and the available A/B/C/D exercise pool.
- 01
Teacher attaches a dynamic set to a lesson
- 02
Strong success keeps or moves the recipe toward more advanced tasks
- 03
Weaker results at a higher level can return the recipe to simpler tasks
- 04
The selected exercise IDs are persisted for later visits
Choose an editable exercise set
Open the exercise-set library and choose static or dynamic delivery based on the available difficulty-labelled tasks.
Common questions
What source formats can I use with adaptive homework?
A static set keeps teacher-defined item order. A dynamic set selects from an exercise pool labelled with A/B/C/D difficulty. Only use source material you are authorised to process, and remove unnecessary personal or sensitive information.
Does adaptive homework use my own material as context?
A static set keeps teacher-defined item order. A dynamic set selects from an exercise pool labelled with A/B/C/D difficulty. The selected description, document, recording, lesson, or response remains the grounding context for the requested workflow.
Can I edit the output from adaptive homework?
For dynamic delivery, the selector reads stored learner success percentages by difficulty for the course subject. Strong success keeps or moves the recipe toward more advanced tasks; weaker results at a higher level can move it back to simpler practice. When the current product workflow creates a saved course, lesson, exercise set, score, or feedback item, the teacher can inspect the supported fields instead of relying on a public-tool output as an automatic import.
What happens to files and recordings uploaded for adaptive homework?
Only upload material you are authorised to process. Keep personal data to the minimum needed for the teaching task, review the result before sharing it, and follow your organisation’s retention and consent policy.
Can a teacher override the result from adaptive homework?
The requested volume determines how many exercises are needed at each difficulty; shortages are filled from the remaining pool. AI can prepare or assess a supported first pass. The educator can inspect and change supported course, lesson, exercise, score, and feedback states; tutoring homework generated from authorised chat context is posted automatically and remains editable afterward.
Which subjects and languages work with adaptive homework?
The requested volume determines how many exercises are needed at each difficulty; shortages are filled from the remaining pool. Support depends on the source quality and requested subject, so educators should review terminology, notation, cultural context, and assessment expectations before use.
How is adaptive homework priced?
AI usage is metered with the same SubSchool AI balance used by course, lesson, homework, and assessment workflows. You can keep drafts private and review the expected operation before publishing or assigning the result.
Can I use adaptive homework without publishing a public course?
The selected exercise IDs are saved for that learner, lesson, and set so later visits return the same selection. Course work can stay in the distinct draft state while it is reviewed. Private, public, and paid are separate course types rather than properties of the same draft.
Turn the page into a real teaching workflow
Keep the result editable, connect it to learners, and preserve teacher review.