Certificate Program in Agentic AI

This week provides a focused refresher on core Python concepts essential for building agentic AI systems, including functions, classes, data structures, and the use of external libraries commonly applied in AI development. 

• Python fundamentals 
• Data structures 
• Functions & classes

This week is focused on key concepts of generative AI, how large language models (LLMs) work, what’s under the hood, and why they behave the way they do. The week concludes with an exploration of generative AI’s business applications across industries and functions such as marketing, finance, healthcare, and productivity. The knowledge you gain here is directly applicable to an agentic AI program designed to improve your practical skills. 

• LLMs 
• Zero-shot prompting 
• One-shot prompting 
• Few-shot prompting

This week is focused on mastering essential prompt engineering techniques to craft effective natural language solutions. Additionally, learners will explore how retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external information, improving the accuracy and relevance of AI-generated responses. 

• Chain-of-thought prompting 
• Vector database 
• Retrieval-augmented generation (RAG)

Domain: Productivity and Workflow Automation 

Project name: Smart Task Prioritizer Agent 

About the project: This project focuses on developing an intelligent agent to automate the processing of employee-submitted expense bills. The agent will analyze submissions and generate expense claim documents that are fully compliant with established company expense policies. 

Skills you will learn: Python Programming, Natural Language Processing (NLP), API Integration, Heuristic Decision Making, Command-Line Interface Development, Task List Management, LLM Integration

This week is focused on learning about agentic AI and its key characteristics, distinguishing it from traditional AI paradigms. Learners will develop an understanding of rational agents and their role as foundational models for autonomous decision-making in intelligent systems. They will also gain insight into how agents communicate with one another using the Model Context Protocol (MCP). This week's content gives you an essential foundation in agent design, something you'll encounter in an AI agents course.

• Agentic AI 
• Agentic workflows
• Model Context Protocol (MCP)
  

This week is focused on the core properties of agents and the types of environments suitable for them. Learners will also compare different types of agents based on their levels of autonomy and the complexity of their goals. This is a great example of the advanced content you’ll find in the agentic AI training online. 

• Autonomy 
• Goal-directedness 
• Reactivity 
• Environment types (PEAS) 
• Perceived agency

This week is focused on examining the AI alignment problem, exploring key ethical challenges and responsible AI principles, analyzing the unique risks posed by agentic AI, and critically assessing agent behaviors through an ethical lens. 

• Key ethical challenges (alignment, safety, responsibility) 
• Responsible AI frameworks 
• Agentic risks

This week is focused on exploring how AI agents plan and reason by examining core paradigms like CoT and ReAct. Learners will learn to trace simple reasoning processes to solve complex tasks using agentic AI and discover how to transform RAG into Agentic RAG. This is essential knowledge for anyone pursuing an agentic AI course online. 

• Planning paradigms (classical, LLM-based) 
• Reasoning (CoT) 
• Reasoning + acting (ReAct) 
• Agentic RAG

Project Name: Automated Research Agent 

About the project: This project involves creating an automated research agent designed to retrieve and synthesize information from multiple data sources, including the internet. The agent will provide comprehensive and iteratively refined answers to user queries, enhancing the depth and accuracy of information retrieval. 

Skills you will learn: Python Programming, Web Scraping (BeautifulSoup, requests), API Integration (e.g., NewsAPI), Natural Language Processing (NLP), Text Summarization, Information Retrieval & Structuring, Code Debugging

This week is focused on core concepts of multi-agent systems (MAS) such as coordination and communication. Learners will analyze strategic interactions through game theory and explore the potential and challenges of integrating large language models (LLMs) into MAS. These are important skills in the Agentic AI training online. 

• MAS concepts (coordination, communication) 
• Game theory basics 
• LLM-based MAS

This week is focused on deepening understanding of reinforcement learning by exploring both foundational and advanced concepts, including deep and verbal RL. Learners will evaluate how different learning paradigms support agent adaptability and lifelong learning. 

• Reinforcement learning (RL) foundations 
• Advanced RL (deep RL, verbal RL) 
• Lifelong learning

This week is focused on exploring key concepts in human-agent interaction such as trust and common ground. Learners will understand the role of simulation in embodied AI and examine the challenges in effective communication and deployment of embodied agents. 

• Human-agent interaction (HAI) (trust, common ground) 
• Embodied AI (simulation, VLA models)

Domain: Customer Support & Automation 

Project Name: Customer Support Chatbot with Knowledge Base Integration 

About the project: This project entails the development of a customer support chatbot engineered to address frequently asked questions (FAQs) concerning a specific product or service. The agent will leverage a predefined knowledge base, employ advanced knowledge retrieval techniques, engage in natural language interactions, and integrate a Large Language Model (LLM) to enhance communication clarity and user experience. 

Skills you will learn: Python Programming, Knowledge Base Management, Natural Language Processing (NLP), Semantic Similarity and Keyword Matching, LLM Integration, Conversational Design, Agent Framework Implementation (LangChain, AutoGen), Retrieval Augmented Generation (RAG), Vector Databases

This week is focused on helping learners deepen their understanding of agentic AI concepts, applications, and strategic implications for their organizations. The sessions will explore the current limitations of agentic AI, including brittleness, scalability, and memory. They will analyze its role in the pursuit of artificial general intelligence (AGI), identify key research challenges in robust reasoning, continual learning, and autonomous tool use, and evaluate the societal and economic impacts of future agentic technologies.