Non-coding software engineers, business analysts, QA professionals, product managers, and technologists who want to design and deploy Generative AI applications without writing code — no machine learning experience required.

No programming experience required, experience playing with ChatGPT or equivalent LLMs will be nice but not required

Course Outline:

1. Foundations of Generative AI and LLMs
   1. History and impact of LLMs
   2. Key terminology: tokens, parameters, training, inference
   3. Why LLMs disrupt industries and workflows
   4. Hands-on: Set up LangFlow workspace and run your first LLM interaction
2. The Art of Prompting
   1. What makes a good prompt?
   2. Zero-shot, one-shot, few-shot prompting
   3. Prompt templates and variables
   4. Hands-on: Build a simple Q&A chatbot with structured prompts
3. Designing Conversations with LLMs
   1. Conversational design principles
   2. Role prompts, context windows, memory
   3. Hands-on: Build a chatbot that maintains context across turns
4. Connecting Data Sources
   1. Introduction to data connectors (CSV, PDF, API, websites)
   2. Pre-processing and cleaning data for LLMs
   3. Hands-on: Upload a CSV and a PDF, extract insights through LangFlow
5. Agents for Automation
   1. What are AI agents?
   2. Tool-using agents, reasoning agents, reactive agents
   3. Hands-on: Build an agent that automates a multi-step research workflow
6. Retrieval Augmented Generation (RAG)
   1. What is RAG and why is it powerful?
   2. Embeddings and vector stores explained simply
   3. Hands-on: Build a knowledge-based chatbot using embeddings + vector DB
7. Building Agentic AI Applications
   1. What is Agentic AI and why is it the next big wave?
   2. How multi-agent collaboration works
   3. Tools for building agent workflows
   4. Hands-on: Multi-agent financial report generator
8. Workflow Automation with n8n
   1. Introduction to n8n: visual workflow builder
   2. Integrating LangFlow applications into n8n workflows
   3. Connecting LLM outputs with real-world tools (Search APIs, Web Scrappers, etc)
   4. Hands-on: Build a pipeline using n8n to summarize website content
9. Capstone Project (Design & Build)
   1. Students form small groups or work solo
   2. Choose a project idea (see below)
   3. Begin building full end-to-end application with data + agents + RAG
   4. Option: Add n8n integration for workflow automation
   5. Instructor and peer feedback during build phase
10. Capstone Showcase & Career Next Steps
    1. Final project presentations
    2. Peer and instructor feedback
    3. Discussion: How to take your skills into your workplace (prototyping, pitching ideas, building Proof of Concepts)
    4. Resources for continued learning and no-code AI toolkits

Training material provided:

1. Slides (PDF)
2. Lab instructions (step-by-step)
3. Prompt templates & LangFlow starter flows
4. n8n starter workflows for AI integration

Hands-on Lab: Students can use either open-source models or OpenAI models. Instructions will be provided to install tools for local machines