Artificial Intelligence

• Overview of the Course
• Understanding Artificial Intelligence
• Differentiating AI and Automation
• Introduction to Generative AI and Its Use Cases
• The Evolution of AI: From Traditional to Generative Models
• Where is AI Today? An Exploration of Current Capabilities
• AI’s Role in Everyday Life
• Understanding Chatbots: What Are They?
• AI-powered Chatbots and Virtual Assistants
• Popular Generative AI Tools and Their Applications
• Common Use Cases of AI and Machine Learning in Daily Life

• The Concept of Cognitive Computing
• Key Terminologies in AI and Related Fields
• A Comparison Between Machine Learning and Deep Learning
• Generative AI Models and Their Characteristics
• Large Language Models: Definition and Examples
• Key Areas of AI: Natural Language Processing (NLP), Speech
• Recognition, and Image and
• video recognition
• What is NLP (Natural Language Processing)?
• The Importance of Prompt Engineering in AI
• AI Integration with Cloud Computing, and the Internet of Things (IoT)

• Understanding AI Agents and Their Functionality
• Exploring the Role of Robotics and Automation in Business
• Transforming Business Models with AI Technologies
• Leveraging Generative AI for Business Innovation
• Becoming a Creator of Value Through Generative AI
• What is Retrieval-Augmented Generation (RAG) and Its Use?
• Implementing AI in Your Business Operations
• Frameworks for Successfully Adopting AI
• Utilizing AI Tools to Enhance Productivity and Workflows
• Human vs. AI Decision-Making: Who Should Lead?

• AI for Communication: Automating Email Writing, Summaries, Reports, and Translations
• AI for Research and Strategic Planning: Conducting Market Analysis, Lesson Planning, and Business Ideation
• AI for Content Creation: From Blog Posts to Visuals, Presentations, and Social Media Content
• AI for Document and Data Management: Analyzing PDFs, Organizing Spreadsheets, and Efficient Notetaking
• AI Tools for Video and Audio
• AI for Productivity: Automating Scheduling, Note-Taking, Reminders, and Meeting Minutes
• Ethical Issues in AI: Addressing Deepfakes, Bias, Data Privacy, and Responsible AI Use

• Responsible Use and Ethical Considerations in AI Development
• Addressing Ethical Issues in Generative AI Technologies
• Why Do Large Language Models Produce Hallucinations?
• Ethical Perspectives from Leading AI Experts and Stakeholders
• The Need for AI Governance and Regulation
• Implementing Ethical Standards in AI Development
• Summary and Key Takeaways from the Course

• Overview Introduction to major LLM platforms: OpenAI GPT-4, Azure OpenAI, Claude, Gemini, Hugging Face
• Setting up API access, authentication, and development environment
• Comparing Python and Node.js/TypeScript SDKs for LLM integration
• Model capabilities, performance, and cost considerations

The Practical Tasks:

• Make API calls to OpenAI, Azure OpenAI, and Claude
• Execute basic prompts in both Python and Node.js
• Compare outputs across different platforms

• The Understanding Zero-shot, Few-shot, and Chain-of-Thought (CoT) prompting
• Crafting role-based prompts and utilizing system-level instructions
• Developing reusable prompt templates for multi-turn conversations
• Managing structured outputs and simulating function calls

Practical Tasks:

• Design complex prompts for real-world business applications
• Create dynamic prompt workflows for interactive Q&A
• Implement structured function calls within prompts

• Key LangChain components: chains, memory, tools, agents
  Execution logic and types of chains
• Integrating external tools like search, calculators, and Python REPL
• Working with LangChain in Python and LangChain.js

Practical Tasks:

• Build document-based Q&A applications using LangChain
• Create conversational agents with memory and context persistence
• Integrate custom tools into agent workflows?

• AI Exploring the “prompt-as-plugin” paradigm with Semantic Kernel skills and memory
• Setting up the Semantic Kernel and registering custom skills
• Orchestrating prompts versus using LangChain for agent management

Practical Tasks:

• Develop and integrate plugins within the Semantic Kernel
• Create intelligent agents for tasks like itinerary planning or FAQ
• Manage and reuse memory between API calls for enhanced context

• Responsible Deep dive into embeddings, vector search, and semantic search
• Understanding and using Vector Databases like FAISS, Pinecone, Weaviate, and Azure Cognitive Search
• Designing a RAG pipeline with LangChain and retrievers

Practical Tasks:

• Ingest unstructured data (PDFs, web pages) and create a vector store
• Implement a full RAG pipeline to improve LLM output accuracy
• Test and compare responses from traditional LLM versus RAG-enhanced models

• Understanding AI agents and the Perceive → Plan → Act cycle
  Task decomposition techniques using LLMs
• Auto-GPT architecture, limitations, and customization
• Controlling agent behavior through parameters and configuration

Practical Tasks:

• Set up and monitor Auto-GPT’s decision-making process
• Define clear goals and observe task breakdowns
• Control agent behavior using parameters like temperature and limits

• Defining agent roles and teamwork dynamics within a system
• Deep dive into CrewAI architecture and agent orchestration
• Building workflows and collaboration mechanisms with LangGraph

Practical Tasks:

• Design a multi-agent system for a complex business problem using CrewAI
• Assign specific roles to agents and define collaborative tasks
• Simulate agent-to-agent communication and task coordination

• Job Understanding AWS Step Functions and Lambda for workflow automation
• Automating processes using Azure Logic Apps & Functions
• Event-driven workflows and orchestrating AI agent tasks
  Logging and monitoring automated agent pipelines

Practical Tasks:

• Automate AI workflows using AWS Step Functions and Lambda
• Trigger automated processes through Azure Logic Apps
• Implement real-time logging and trace observability for agent pipelines

• Working with Azure OpenAI endpoints and models for agent deployment
• Building and integrating bots with Azure AI Studio & Copilot Studio
• Implementing enterprise-grade AI solutions with Azure Cognitive Services

Practical Tasks:

• Deploy an AI agent using Azure Functions and OpenAI APIs
• Build a chatbot with integration to Teams or Web channels
• Securely implement RAG using Azure Cognitive Search for enhanced AI capabilities

• Exploring real-world applications: HR automation, legal assistants, customer support
• Measuring ROI and articulating the value of AI solutions
• Ethical considerations, data privacy, and implementing fallback mechanisms

Capstone Project:

• Design and develop a fully functioning AI agent for a business use case
• Present the solution architecture, capabilities, and real-world application
• Evaluate the solution’s performance and assess its impact on business ROI

• Gen AI Engineer
• Prompt Engineer
• AI Consultant
• AI Business Analyst
• AI Program Manager
• AI Architect
• AI Ethics Specialist