AI for Developers: Course Orientation

Welcome to this course. This orientation gives you the same structure serious learning platforms use: prerequisites, outcomes, timeline, and execution expectations.

What You Will Learn

By the end of this course you will be able to:

explain tokens, embeddings, and transformer behavior in practical terms
build and evaluate prompt workflows for reliable outputs
ship an AI chatbot with tool-calling patterns
design and implement a production-ready RAG pipeline

Prerequisites

Python basics (variables, functions, APIs)
basic JSON/HTTP understanding
no prior deep-learning framework required

Recommended:

prior experience with one backend framework
comfort reading code snippets and logs

Course Structure (Chapter Flow)

LLM Foundations
Understand models, context windows, tokens, embeddings, and constraints.
Prompt Engineering
Design prompt templates and structured output contracts.
Chatbot Build
Build an application layer around model calls.
Agents and Tool Calling
Add multi-step workflows with tool execution.
RAG in Production
Add retrieval, citations, and evaluation.

Weekly Study Plan

6-8 hours per week
2 theory sessions + 2 coding sessions + 1 review session
publish at least one notebook or project progress update weekly

Required Tools

Python
Jupyter/VS Code
FastAPI (recommended for APIs)
model provider SDKs
optional: vector database for RAG experiments

Completion Criteria

To complete this course properly:

finish all lessons in order
implement at least one working chatbot
implement one RAG workflow with citations
publish a short architecture and lessons-learned document

FAQ

Do I need advanced ML math?
No. You need practical engineering discipline more than advanced math.

Can I finish faster?
Yes, but do not skip build tasks. They are the core learning mechanism.

What comes next?
Continue with the AI/ML/NLP research track for deeper NLP, transformers, and portfolio work.

Course Orientation: Roadmap, Prerequisites, and Study Plan