AI Agents and Agentic AI: concepts and vocabulary | Complete Generative AI: From Foundations to Production
A self-paced 26-week learning path with 15 modules: AI foundations, Python, machine learning, transformers, LLMs, prompts, APIs, embeddings, RAG, frameworks, agents, customization, multimodal AI, Spring Boot with React, and production LLMOps. Includes 15 practical assignments and three portfolio projects.
Prerequisites: Begin with basic computer skills. Programming is introduced in Weeks 2–3. Use a local Python environment for coding labs; Java and React experience helps in Weeks 21–22. Model downloads, provider accounts and deployment resources are optional learner-managed dependencies. The 26-week schedule is suggested; reading estimates exclude independent project work.
Learning goals
Agents versus chatbots
Planning and controlled tools
ReAct-style workflows
Stateful and multi-step agents
LangGraph and orchestration
Multi-agent systems
Human approval and guardrails
Failure recovery and evaluation
Understand the foundations
An agent chooses steps or tools to pursue a goal, whereas a simple chatbot may only produce a response. A workflow can be mostly deterministic with a model used at selected decision points. ReAct-style patterns alternate action proposals and observations, but application logs should capture concise decisions and tool results rather than demand private hidden reasoning. More autonomy or more agents increases coordination and failure surfaces; it is not automatically an improvement over a small bounded workflow.
Connect the ideas
Represent state explicitly: goal, eligible job IDs, attempted tools, remaining budget and completion status. LangGraph provides graph-based orchestration concepts such as nodes, edges and persistent state. Keep allowed transitions and tool schemas in application code. Tools must check identity and object access each time they execute. Limit steps, elapsed time and cost, and define handling for failed tools, repeated actions and stale state. Multiple agents must share only permitted context and cannot grant one another new permissions.
Checkpoint: explain these concepts in your own words, then describe one failure that the design must detect. Use synthetic or permissioned data throughout the course.
01. Introduction to Artificial Intelligence · Week 1
02. Python Programming for Gen AI · Weeks 2–3
03. Mathematics and Machine Learning Foundations · Week 4
04. Deep Learning and Transformers · Weeks 5–6
05. Large Language Models (LLMs) · Weeks 7–8
06. Prompt Engineering · Weeks 9–10
07. Generative AI APIs and Application Development · Week 11
08. Embeddings and Vector Databases · Weeks 12–13
09. Retrieval-Augmented Generation (RAG) · Weeks 14–15
10. LangChain, LlamaIndex and AI Frameworks · Week 16
11. AI Agents and Agentic AI · Weeks 17–18
12. Fine-Tuning and Model Customization · Week 19
13. Multimodal Generative AI · Week 20
14. Gen AI with Java Spring Boot and React · Weeks 21–22
15. Production Gen AI, LLMOps and Capstone · Weeks 23–26