meta data for this page

AI Enrichment Tools

Overview

LEAST includes a full AI enrichment suite backed by the Anthropic Claude API. It helps educators and administrators enrich lesson metadata, classify content, surface discovery connections, and govern AI-generated material before it goes live.

Live AI Features

Code Feature Status Where to find it
AI-01 Lesson Markup — AI Insights modal Live Lesson page → AI Insights button
AI-02 IWTB Role Enrichment — 700+ career roles Live Admin → IWTB → Role list
AI-03 Role-Lesson Semantic Graph — 734 scored links Live Admin → IWTB → Role-Lesson links
AI-04 Editorial Governance Workspace Live /educator/ai-review-queue.php
AI-06 EKOS Classification — UDC + IFQ alignment Live System → EKOS → Awaiting review

AI-01: Lesson Markup (AI Insights)

Every published lesson has an AI Insights button that opens a modal with AI-generated learning support:

  • Overview — plain-language summary of the lesson
  • Key Points — bullet list of core concepts
  • Why This Matters — real-world relevance
  • Suggested Next Steps — what to explore after this lesson
  • AI Instructions — guidance for AI systems using this lesson with learners
  • Sources — references to materials used in generation

Content is reviewed via the AI-04 governance workspace before going live. Stored in strLesson_AI_Markup and rendered as CommonMark on the lesson page.

AI-02: IWTB Role Enrichment

The I Want To Be (IWTB) engine covers 700+ career roles, each AI-enriched with:

  • Role background and description
  • Suggested next steps for learners
  • Key figures in the field
  • Recommended books
  • Related TV shows and films
  • Salary and career outlook data

Roles are browsable from the learner dashboard and discoverable via the Discover page.

AI-03: Role-Lesson Semantic Graph

Claude scores how well each lesson matches each career role (0–100). 734 approved links are live, powering:

  • “Lessons for this role” on IWTB role pages
  • Personalised lesson recommendations
  • Curriculum gap analysis per role

AI-04: Editorial Governance Workspace

Navigate to /educator/ai-review-queue.php to:

  • Review AI-generated lesson markup awaiting approval
  • Accept, edit, or reject individual fields with field-level rollback
  • Track OG / AI / Tags completion status per lesson
  • Monitor which lessons are missing markup

AI-06: EKOS Classification

The European Key Occupations Standard (EKOS) engine links lessons to:

  • UDC (Universal Decimal Classification) subject categories
  • IFQ (Irish Framework of Qualifications) levels 1–22

Review and approve EKOS suggestions at /system/workflow_content.php.

Content Pipeline

The AI content pipeline generates complete lesson bundles from a topic list and injects them via the Lesson Injection API. The pipeline is fully PHP-native — no Python or external packages required on the server.

To queue a pipeline run:

  1. Add topics to projects/topic_list.json
  2. The cron worker (job_type = pipeline_ingest) picks up the job
  3. Claude generates a complete lesson bundle per topic
  4. Lessons land in the review queue at /educator/lesson-review-queue.php

topic_list.json format: 

[
  {
    "topic": "How to send an email",
    "context": "Digital skills for beginners",
    "learning_objective": "Compose and send a basic email",
    "target_level": "beginner",
    "materials": ["https://youtube.com/watch?v=example"],
    "notes": "Prefer practical framing."
  }
]

Lesson Review Queue

After pipeline ingestion, AI-generated lessons land in the Lesson Review Queue at /educator/lesson-review-queue.php:

  • Lesson title and summary
  • OG / AI / Tags completion indicators
  • Source (ai_pipeline, manual, etc.)
  • Batch ID for traceability

Technical Reference

  • Model: claude-haiku-4-5-20251001 (configurable via ANTHROPIC_MODEL in env.php)
  • Prompt caching enabled — ephemeral cache blocks reduce cost on repeated runs
  • PHP client: cron/lib/claude_client.php — reusable for other cron jobs
  • API key: ANTHROPIC_API_KEY in lib/const/env.php