Public transparency artefact

EduZen AI Tutor — AI System Card

Version 0.1.0-foundation · Issued 7/8/2026, 9:24:01 AM

Purpose

Adaptive tutoring for GCSE / 11+ / KS3 learners aged 9-18. The system explains, hints and assesses but does not award formal grades.

Risk class: high-risk (EU AI Act Annex III §3 — education)

Model routing

  • default tutor
    claude-sonnet-4.5
  • mark feedback
    gpt-5.2
  • image ocr
    gemini-3-flash

frontier large language models accessed via the Emergent Universal Key — Anthropic Claude, OpenAI GPT, Google Gemini

We do not train models on children's data. Period.

Guardrails

  • PII pre-filter and post-filter (regex + classifier + LLM-judge)
  • Refusal taxonomy: out_of_scope, unsafe, ambiguous, off_curriculum, requires_human, requires_parent, regulated_advice, exam_cheat
  • Confidence score (logprobs + self-consistency n=3) — answers below 0.6 are flagged
  • Hallucination tripwire against curated curriculum knowledge base
  • No cross-session memory for under-13 by default

Human oversight

  • Teacher-in-the-loop for school deployments (transcript visibility)
  • Parent-in-the-loop for B2C (weekly digest + on-demand transcripts)
  • Monthly red-team panel + safeguarding review

Safeguarding

Safeguarding overlay shown to child; session frozen; Designated Safeguarding Lead alerted within 5 minutes.

Audit logging

Retention: 7 years · Storage: MongoDB append-only with hash chain (sha256, prev_hash linked).

Show logged fieldslog_id · ts · user_id_hash · session_id · role · child_age_band · prompt_hash · prompt_category · model · model_version · system_prompt_hash · response_hash · confidence · refusal_flag · safety_flags · latency_ms · cost_tokens

Contact

EduZen AI
by TripZen · Travel Smarter. Learn Better. Live Fuller.
Curriculum Aligned
UK, India, US & more
Child Safe
Built for students' safety
Privacy First
Your data is protected
Secure Platform
Enterprise grade security
© 2026 TripZen Ltd. All rights reserved.