Your AI-powered in-lecture companion. Context-aware, persistent, and built for how you actually learn.

• Python 3.10+
• Node 18+
• AWS credentials configured locally (already done)
• AWS Bedrock enabled in us-east-1 with anthropic.claude-3-5-sonnet-20241022-v2:0 model access

cd lectern/backend
pip install -r requirements.txt
python app.py

Backend runs at http://localhost:5000

cd lectern/frontend
npm install
npm run dev

Frontend runs at http://localhost:3000

1. localhost:3000 — Onboarding (name, courses, learning style, optional syllabus paste)
2. /lecture — Hit "Start Lecture" — watch transcript stream with live smart alerts
3. After lecture ends — hit "Get Summary" for Bedrock-generated post-lecture recap
4. /professor — Confusion heatmap across all topics, with recommended actions

• AWS Bedrock (us-east-1) — Claude 3.5 Sonnet via bedrock-runtime
  • Syllabus parsing → concept graph + priority scores
  • Post-lecture summary generation
  • All AI reasoning runs through Bedrock

[Next.js Frontend]
      ↕ fetch / SSE
[Flask Backend (Python)]
      ↕ boto3
[AWS Bedrock — Claude 3.5 Sonnet]