Implement AI-powered personalised learning lab with Cloudflare Workers AI

[Copilot]

Greenfield implementation of LearnPilot — an adaptive learning platform backed by Cloudflare Workers AI (@cf/meta/llama-3.1-8b-instruct). The repo previously contained only a README and LICENSE.

Data layer (learning/models.py)

• Topic, Course, Lesson — content hierarchy
• LearnerProfile — skill level, learning style, XP, day streaks
• AdaptivePath / PathLesson — ordered AI-generated lesson sequences per learner
• LearningSession / Message — tutoring conversation persistence
• Progress — per-lesson score, completion, attempt count, XP award

Cloudflare AI integration (learning/ai/)

• cloudflare_ai.py — thin HTTP client for the Workers AI REST API; transparently routes through a deployed Cloudflare Python Worker when CLOUDFLARE_WORKER_URL is set
• tutor.py — IntelligentTutor: structured prompts for concept explanation (adapts to skill level + learning style), practice question generation, answer evaluation (returns score 0–1 / feedback / correct_answer), conversation continuation, and session summaries
• adaptive.py — AdaptiveCurriculum: generates ordered lesson paths as JSON, recommends next lesson based on history, adjusts difficulty from recent scores, produces progress insights

# Direct API usage example
tutor = IntelligentTutor()
result = tutor.evaluate_answer(
    question="What is a Python decorator?",
    learner_answer="A function that wraps another function",
    topic="Python Functions",
)
# → {"score": 0.85, "feedback": "…", "correct_answer": "…"}

Cloudflare Python Worker (workers/)

• workers/src/worker.py — edge worker using env.AI binding; exposes /ai/chat, /ai/explain, /ai/practice, /ai/evaluate, /ai/path endpoints with CORS
• workers/wrangler.toml — deploy with wrangler deploy (Python workers + AI binding)

Django app (learning/)

• Views: dashboard, course list/detail, session start/chat/end, AJAX evaluate API, progress with AI insights
• seed_data management command seeds 4 topics, 6 courses, 21 lessons
• 50 unit + integration tests covering models, AI modules, and HTTP views

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• api.cloudflare.com
  • Triggering command: /usr/bin/python python manage.py test tests --verbosity=2 (dns block)
  • Triggering command: /usr/bin/python python manage.py test tests --verbosity=1 rd --local /usr/local/.ghcup/bin/git credential.helpegit (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

AI-powered personalized learning lab that adapts to each learner in real time. Combines natural language processing, adaptive curricula, intelligent tutoring, and progress tracking to create a dynamic educational experience with interactive explanations, guided practice, and continuous feedback. uses Cloudflare AI python workers

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.