EU AI Act · Article 13 transparency

How Edaptic's AI systems work

This page describes every AI system in Edaptic — what it does, how it makes decisions, what it can and can't do, and how humans stay in control. Required under the EU AI Act for high-risk AI systems.

Edaptic is intended for users aged 16 and older. Account creation requires affirmation of age and the platform refuses registrations that declare an age under 16.

AI as an assistant to instructors — and as a tutor for students

Edaptic uses AI in two distinct ways. For instructors, AI is an optional drafting tool: it can suggest concept taxonomies, draft slide explanations, and generate assignment questions. Nothing AI-produced reaches students without the instructor explicitly reviewing, correcting if necessary, and confirming accuracy via a mandatory approval step. The instructor is always the author of record. For students, AI operates as a real-time tutor: your questions in the chat are answered live by a large language model, and your first explanation for each slide is served from the instructor's approved content (or labelled as an AI draft if the instructor hasn't reviewed it yet). All AI-generated content is clearly labelled throughout the interface.

Edaptic is classified as a high-risk AI system

Because Edaptic assesses student competence and influences access to educational content, it falls under Annex III, Category 3 of the EU AI Act — AI systems used in education to evaluate learning outcomes or steer the learning process. We've designed for this classification from day one.

Reference: Regulation (EU) 2024/1689, Annex III, paragraph 3(a)

The AI systems, one by one

Edaptic uses several AI-related systems. Five are described first — the AI tutor, the AI grader, the Evidence-Based Mastery tracker, the rule-based risk indicator, and the adaptive recommendation engine. Two further optional systems are described after them: a speech-to-text system that only runs when your course turns on voice input, and an AI governance layer that only runs when your institution turns it on. Each is described with its purpose, decision logic, known limitations, and the human oversight in place.

AI tutor

Large language model — generative AI

The AI tutor is the live, conversational AI you interact with while studying. When you open a slide, you can request an "Intuition" or "Technical" explanation — the system first checks whether your instructor has already prepared and approved an explanation for that slide. If so, that instructor-curated content is shown (with a ✅ Human Approved badge). If not, an explanation is generated on the fly and shown with a 🤖 AI Draft badge, indicating it has not yet been instructor-reviewed.

After the initial explanation, any follow-up questions you type in the chat are answered in real time by a large language model. These live responses are AI-generated without per-message pre-approval. The persistent notice at the top of the chat identifies the model being used.

How it decides what to say: A system prompt is constructed dynamically from the current slide, your instructor's configured persona, your audience level, and your domain. This prompt, together with your message, is sent to the configured large language model (such as GPT-4o, Claude, or Gemini). The model generates a response token by token. It does not access the internet, your grades, or other students' data during this process.

Input
Your message, slide content, conversation history (current session), study domain, audience level
Output
Text response with optional LaTeX math, code blocks, and citations
Model used
Configured per course by your instructor. Shown in the chat interface as a persistent notice at the top of every chat window.
Affects your grades?
No. Chat interactions do not affect any academic record or score.
  • Live chat responses can be incorrect or misleading — always verify important claims against course materials or your instructor's approved explanations
  • Has no memory between sessions — each new session starts fresh
  • Cannot access the internet, your grades, or other students' data
  • An explanation shown as "🤖 AI Draft" has not yet been reviewed by your instructor — treat it with appropriate caution
  • May reflect biases present in its training data

AI grader

Large language model — scoring and feedback

When you submit a written answer on an assignment, the AI grader evaluates it against the question and a rubric set by your instructor. It produces a numeric score and written feedback explaining the score.

How it decides your score: Your answer, the question text, the model answer or key concepts, and the rubric are sent to the grading model. The model returns a score (an integer between 0 and the question's maximum points, typically 10) and a justification in a structured format. The score is type-checked and clamped to the valid range before being stored. If the model fails or returns malformed output, the system retries up to two more times before marking the question as "grading failed".

Input
Your written answer, the question, the rubric, maximum points
Output
Integer score (0 to max_points, typically 10) and written feedback per question
Affects your grades?
Yes — this score contributes to your assignment result and mastery profile
Can you contest it?
Yes — request instructor review on any AI-graded answer
  • May misinterpret creative, unconventional, or multilingual answers
  • Cannot evaluate diagrams, handwritten work, or uploaded images
  • Rubric interpretation depends on the model — different models may produce slightly different scores for the same answer
  • A written answer counts as correct for the mastery calculation when the AI score is at least 60% of the question's max points — this threshold is fixed and may not suit all question types

Mastery tracker

Evidence-Based Mastery Score — not a neural network

After every quiz or assignment answer, the mastery tracker updates a score for each concept tested. This is not an AI model — it's a transparent weighted ratio of correct evidence over total evidence per concept. The full specification lives in doc/evidence_based_mastery_model.tex.

How it calculates your mastery: Each answer becomes one piece of evidence linked to the canonical topics it tests. Your score for a concept is the weighted fraction of correct evidence, with recent work counting more than older work.

mastery_score = 100 × Σ(weight × correct × decay) / Σ(weight × decay)
Evidence weights reflect how strong each kind of work is as a signal: practice = 0.5, MCQ and live quiz = 1, written = 3, exam and report = 5. Instructors can override these per course.

Recency decay is piecewise-linear and explainable in one sentence: evidence newer than 30 days counts in full, then tapers linearly to half weight over the next 90 days, and stays at half weight after that. Older work still counts — just less.

The score is paired with a band (Needs support 0–39, Developing 40–69, Almost secure 70–84, Secure 85–100) and a confidence level (None / Low / Medium / High) derived from how much evidence has accumulated. A 90% score on three questions is correctly tagged as low-confidence.
Input
Whether your answer was correct or incorrect, the type of work (practice / MCQ / written / exam / live quiz / report), and which topic(s) the question tests
Output
Mastery score 0–100, band, confidence level, and the underlying evidence count per topic
Affects your experience?
Yes — mastery scores influence adaptive difficulty and feed the risk indicator
Is it an AI model?
No — it's a deterministic weighted average. The same evidence always produces the same score, regardless of the order it was recorded.
  • Assumes each answer is independent — doesn't account for fatigue, stress, or contextual factors
  • Treats written and report answers as correct for the mastery calculation if the AI grader scores them ≥ 60%, which folds grader uncertainty into the score
  • A small number of recent answers can move the score quickly when there is little prior evidence — the confidence level flags this
  • Source weights and decay are course-wide rather than personalised per student

Risk indicator

Rule-based engine — not AI

The risk indicator is an advisory label shown to your instructor that estimates whether you might benefit from additional support. It is not an AI system — it's a rule-based engine that evaluates a small set of explainable rules against your Evidence-Based Mastery state.

risk_level ∈ { low · medium · high }
Each evaluation runs a rule pack (default values below; instructors can override per course in the course settings) against your current mastery scores and the skills required by upcoming assignments:

Weak-skill threshold: a topic is "below threshold" when its mastery score is under 70%.
Medium-risk rule: fires when three or more required topics are below the threshold.
High-risk rule: fires when at least three required topics are below the threshold and at least two of those skills are needed for the next assignment.

When a rule fires, the engine records the rule that triggered it (main reasons) and a list of explainable next steps (recommended actions) such as "review Linear Regression" or "complete the next practice set". Both are surfaced to your instructor; nothing is hidden behind a black-box score. These labels are advisory — they do not trigger any automated academic consequence.
Who sees this?
Your instructor only. Not visible to other students. Not on your academic record.
Automated consequences?
None. The label is advisory. It does not affect your grades, enrollment, or academic standing.
Can you see the reason?
Yes — every risk evaluation stores the rule(s) that fired and the recommended next steps. Your instructor can share these with you on request.
Versioned?
Yes — every evaluation is stamped with the active course graph version, so a snapshot can be replayed against the taxonomy that produced it.
  • Does not account for extenuating circumstances (illness, part-time study, late enrollment)
  • A student with very little evidence may be flagged simply because there's no signal yet — the confidence level on the underlying mastery is the better indicator early in a course
  • Default thresholds (70% mastery; three weak skills; two required for the next assignment) may not suit every course structure equally

Adaptive recommendation engine

Weighted heuristic — not a neural network

The adaptive engine suggests personalised settings for your learning experience: difficulty level, teaching style, and learning persona. These are suggestions — you can override all of them on your Preferences page.

How it decides: Three signals feed the recommendation, ordered by influence: your assignment mastery scores (primary), your session behaviour such as message length and question frequency (secondary), and your feedback ratings on AI responses (a small confirmation signal). The output is a recommended audience level and teaching persona, not a binding decision.

Can you override it?
Yes — everything it recommends can be changed in Preferences. Your overrides persist.
Affects your grades?
No. It changes how content is presented, not how you are evaluated.
  • Early in a course, with limited data, recommendations may be generic or inaccurate
  • Infers learning style from behavioural signals which may not reflect your actual preference
🎙

Speech-to-text (optional)

OpenAI Whisper — voice transcription

If your instructor turns on voice input for your course, you can speak instead of type. Your short recording is sent to OpenAI's Whisper service, which converts the speech to text. Only the text is kept — it becomes your answer, exactly as if you had typed it; the audio recording is not stored. This feature is controlled at two levels: your instructor must turn it on for your course, and the platform operator must allow it for the whole deployment. An operator that keeps all data inside the EU/EEA can switch it off platform-wide, in which case it is unavailable regardless of any course setting.

Input
A short audio recording (capped at 10 MB) that you choose to record
Output
A text transcript of what you said
Provider
OpenAI Whisper (whisper-1), servers in the United States
Affects your grades?
No. It only turns your speech into text for you to use.
  • Audio cannot be cleaned of personal identifiers the way typed text is — so this feature is off unless your course enables it and the operator allows it platform-wide
  • Transcription can mishear accents, background noise, or technical terms
  • Edaptic does not store the recording; it is transcribed and discarded
🛡

AI governance layer (optional)

TrustLayer — policy checks and audit, only when your institution enables it

If your institution switches AI governance on, a copy of the tutor prompt and the tutor's response — with the same personal-data placeholders already applied as for any other AI request — together with a pseudonymous account reference and your course identifier is sent to TrustLayer. TrustLayer runs policy checks and keeps an audit record. It does not generate any content you see and it does not change what the tutor says to you. This is off by default.

Input
The (already personal-data-scrubbed) tutor prompt and response, plus a pseudonymous account reference and your course
Output
A policy/audit verdict used for governance; in the default "shadow" mode it is recorded and otherwise discarded
Operated by
An affiliated company under common control with the Edaptic group, acting as a separate processor under an intra-group data processing agreement. Inactive by default — it processes data only if your institution explicitly enables AI-governance mode.
Affects your grades?
No. It checks and records; it does not score you.
  • Off by default; only active if your institution turns AI governance on
  • When the operator sets it to "enforce" mode, all tutor traffic — including EU-hosted providers — is routed through TrustLayer, so its hosting region then determines where processing happens

How AI content is marked

You will always be able to distinguish AI-generated content from human-authored content. Here's the marking system:

WhereMarkingWhat it means
Chat interface 🤖 AI notice A permanent strip at the top of every chat showing the AI model name and linking to this page. Cannot be dismissed.
Slide explanations 🤖 AI Draft or ✅ Human Approved "🤖 AI Draft" means the explanation was generated by AI and has not yet been reviewed by your instructor. "✅ Human Approved" means your instructor confirmed accuracy via a mandatory checkbox in the approval modal.
Assignment feedback 🤖 Graded by AI Badge on each AI-graded answer. Plus a pre-submission disclosure banner (EU AI Act Art. 22): "Written answers were graded by an automated AI system." This appears before you submit any written assignment.
Quiz questions AI-generated Questions were generated by AI. Your instructor must confirm review in the "Confirm & Publish" modal — ticking "I have reviewed all questions in this assignment and confirm they are accurate and appropriate for students" — before students can see them.
Mastery scores Calculated Not AI — a weighted ratio of your correct evidence over total evidence per topic (Evidence-Based Mastery)
Risk indicator Calculated Not AI — produced by a rule-based engine over your mastery state. Visible to your instructor only.

Human oversight at every decision point

The EU AI Act requires human oversight for high-risk AI systems. Here's where humans are in the loop in Edaptic:

Quiz and assignment questions

Instructors must confirm review in the "Confirm & Publish" modal — ticking "I have reviewed all questions in this assignment and confirm they are accurate and appropriate for students" — before students can access any assignment. Assignments can also be saved as drafts for staged review before publishing.

Slide explanations

AI-generated explanations show a "🤖 AI Draft" badge until the instructor explicitly approves them. The "✅ Human Approved" badge only appears after the instructor checks "I have reviewed this AI-generated content and confirm it is accurate and appropriate for students" in the Confirm & Approve modal.

Concept taxonomy

The AI proposes a concept structure. The instructor must review, edit, and explicitly apply it — including a safety confirmation for replacements.

AI grading

Every AI-graded answer shows a "🤖 Graded by AI" badge. Students can click "Request Human Review" on any answer. Instructors have a dedicated review queue with per-question score and feedback override. Instructor-overridden grades always replace AI scores.

Risk indicators

Risk labels are advisory only. No automated academic actions are taken. The instructor interprets and acts on the signal using their own judgment.

Adaptive settings

All adaptive recommendations can be overridden by the student in their Preferences page. The system respects manual overrides.

Which AI provider sees your data?

Edaptic doesn't host its own large language models. When you chat with the AI tutor, when an assignment is graded, or when an instructor generates content, the request is sent to one of the platform's configured providers. For these chat, grading, and authoring features, the set of providers your deployment can reach is controlled by the platform admin via the API-key configuration; an API key that isn't configured cannot be reached at all.

One further OpenAI service sits slightly outside that key-controlled set today: the optional voice transcription described above (whisper-1). It is listed in the table below for completeness.

Provider Where inference runs EU/EEA?
OpenAI (GPT)United StatesNo (EU-US Data Privacy Framework)
Anthropic (Claude)United StatesNo (EU-US Data Privacy Framework)
Google (Gemini)United StatesNo (EU-US Data Privacy Framework)
MistralFranceYes
NTNU HPC (Mistral / Qwen on-prem)NorwayYes (EEA)
OpenAI Whisper (whisper-1) — voice transcription, only when your course enables itUnited StatesNo (EU-US Data Privacy Framework)

Before any of these providers receives user-typed text, the platform runs a PII scrubber that replaces categorical personal data (email addresses, phone numbers, Nordic national identifiers, credit-card-shaped numbers) with typed placeholders. So even when a request is sent across the Atlantic, the recipient does not see those specific identifiers.

You can see which provider made any individual decision affecting you by asking your instructor for the decision trace for that response — the audit log records the provider name on every AI grade.

Your right to contest AI decisions

Under both the EU AI Act and GDPR, you have the right to understand and challenge decisions that affect you. Here's how:

You can always request human review

No AI-generated score, label, or recommendation in Edaptic is final. You have specific mechanisms to contest each one:

  • AI-graded assignment: Click "Request instructor review" on any graded answer. Your instructor will re-evaluate it personally.
  • Mastery score: Each score is auditable — your instructor can show you the evidence events that fed into it. If you believe a piece of evidence is wrong (for example, a misgraded written answer), request human review on that answer; the override deletes the affected evidence and replays the corrected verdict through the mastery pipeline.
  • Adaptive recommendations: Override any recommendation in your Preferences page. Your manual settings always take precedence.
  • Risk indicator: If you're aware your instructor has flagged you as at-risk and you believe the classification is wrong, contact your instructor directly. The label is advisory and carries no automated consequences.
  • AI-generated content: If you find an error in an AI-generated explanation or quiz question, use the feedback button to report it. Your instructor will be notified.

Questions about AI in Edaptic?

Contact the development team

If you have questions about how any AI system works, want to understand a decision that affected you, or want to report an error, contact us at adil.rasheed@ntnu.no.

For GDPR-specific data rights (access, deletion, portability), see the Your data in Edaptic page.

This page describes AI systems in Edaptic version 2.6 (May 2026) and is published in accordance with EU AI Act Article 13 transparency requirements. It will be updated when systems change materially.