Course Overview
Interns move from if-then programming to data-driven systems: building simple models in Colab, using LLM APIs, automating AI workflows in n8n, and adding one practical AI feature to their concept. Tools: Google Colab, VS Code, n8n, scikit-learn, Google Teachable Machine, Gemini or other LLM API, GitHub. The course runs for 4 weeks (12 sessions), with the last session used to showcase and evaluate your deliverable.
Course Curriculum & Modules
Course Deliverable
AI-Enabled Concept Prototype: one working AI feature tied to the product concept (for example classification, a chatbot, or an n8n AI workflow), a Colab notebook or n8n workflow export, an evaluation table (accuracy or output quality on test cases), a one-page bias and data-privacy note, and a demo.
Software Engineering Department Pathway
Software Engineering covers applied AI/ML integration, full-stack web/mobile application architecture, DevOps containerization (Docker/Kubernetes), cloud security, high-throughput microservices, and enterprise architecture.
Computer & Hardware Requirements
Key Learning Outcomes & Benefits
- ✓Explain how AI differs from traditional programming and walk through the ML pipeline.
- ✓Train and evaluate simple classification and regression models in Google Colab.
- ✓Call an LLM API and build AI workflows in n8n.
- ✓Add one working AI feature to your concept and write a bias and data-privacy note.
