Changelog

All notable changes to the AI-Generated Content Integrity Framework (ACIF) will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

1.0.0 — 2026-04-08

Complete 41-page ACIF Framework PDF with Harmony Digital Consults branding
Full Markdown version of the framework for easy reference and version control
10 framework sections covering scope, principles, risk classification, age bands, hallucination detection, verification pipeline, data privacy, governance, standards alignment, and implementation
3 appendices: Quick Reference Checklists, AI Content Registry Template, Glossary of Key Terms
References section with clickable source URLs

4 Risk Tiers (Low, Medium, High, Critical) with defined gate requirements for each
6 Age Bands with vocabulary, theme, and complexity specifications per band
Five-Gate Verification Pipeline: Pre-Delivery Screening, Factual Verification, Age-Appropriateness Review, Curriculum Alignment Check, Final Approval and Labelling
FACT Hallucination Detection Method: Find, Assess, Cross-reference, Tag
Hallucination Log specification for institutional tracking of AI errors
AI Content Registry specification for approved content audit trails
Governance structure: AI Content Integrity Committee (ACIC) with defined roles and responsibilities
Escalation procedure for unresolvable verification issues

Dashboard with institution stats, pipeline visualisation, and quick actions
Risk Tier Classifier — interactive 5-question questionnaire
Five-Gate Verification Pipeline — sequential checklists with gate locking and reviewer sign-off
Age-Appropriateness Checker — band selector with allowed/prohibited theme lists
Hallucination Log — form, searchable table, summary analytics, CSV export
Content Registry — filterable table with expandable detail view and CSV export
localStorage persistence for all data
Mobile-responsive design
Harmony Digital Consults teal branding (#01696F)