Gen AI & Agentic AI Specialization
At Scholars Venue, we'll help you connect what you learn to what you do in real-world projects, illustrating how data flows through systems step-by-step with clear and engaging visuals.
Download
Course Syllabus
Trail Videos
Free
Python for Generative AI
Python Foundations
- Why Python for Gen AI?
- Python Setup and VS Code
Python Fundamentals
- Variables and Data Types
- Conditions and Loops
- Functions and Modules
- Lists, Dictionaries, and JSON
Python for AI Development
- APIs and Environment Variables
- Working with Files and Documents
- Error Handling and Logging
- Building Reusable Python Applications
AI for Python
- AI-Assisted Python Development
Industry Updates & New Features
- Python Tools for Gen AI
Generative AI & LLMs
Introduction to Generative AI
- What is Generative AI?
- How Large Language Models Work
- Tokens, Context Windows, and Parameters
LLM Ecosystem
- OpenAI, Gemini, Claude, and Open Models
- Choosing the Right LLM
- Using LLM APIs
Prompt Engineering
- Prompt Engineering Basics
- System Prompts and User Prompts
- Few-Shot Prompting
- Structured Output and JSON
- Prompt Testing and Improvement
LLM Application Development
- Building a Basic Chatbot
- Conversation Memory
- Streaming Responses
- LLM Error Handling and Cost Control
AI Safety Basics
- Hallucinations and Limitations
- Privacy and Responsible AI
- Prompt Injection Basics
Industry Updates & New Features
- LLM Trends and New Models
LangChain & LLM Frameworks
Introduction to LangChain
- Why LangChain?
- LangChain Setup
- Models, Prompts, and Output Parsers
Chains and Workflows
- Simple Chains
- Sequential Chains
- Runnable Interfaces
- Structured Outputs
Memory and Conversation
- Chat History
- Conversation Memory
- Stateful LLM Applications
Tools and Function Calling
- Introduction to Tools
- Function Calling
- Custom Tools
- Tool Error Handling
LangChain Development
- Building a Document Chatbot
- Building an AI Assistant
- Testing and Debugging Chains
Industry Updates & New Features
- LangChain Ecosystem Updates
RAG Systems
Introduction to RAG
- What is RAG?
- Why RAG is Needed
- RAG Architecture
Document Processing
- Loading Documents
- Text Cleaning and Chunking
- Metadata and Document Structure
- Embeddings
Vector Databases
- Introduction to Vector Databases
- Chroma and FAISS
- Pinecone and Cloud Vector Databases
- Storing and Retrieving Embeddings
Retrieval Techniques
- Similarity Search
- Metadata Filtering
- Hybrid Search
- Re-Ranking Results
Building RAG Applications
- Basic RAG Chatbot
- RAG with Citations
- Multi-Document RAG
- RAG Evaluation
Advanced RAG
- Query Rewriting
- Parent and Child Chunking
- Agentic RAG
- RAG Performance Optimization
Industry Updates & New Features
- RAG Tools and Best Practices
MCP & AI Tools
Introduction to MCP
- What is Model Context Protocol?
- MCP Architecture
- MCP Clients, Servers, and Tools
Building MCP Servers
- MCP Server Setup
- Creating MCP Tools
- Creating MCP Resources
- MCP Prompts
Connecting AI to Tools
- Connecting LLMs with MCP
- Database Tools
- File and Document Tools
- API Tools
MCP Security
- Tool Permissions
- Authentication and Secrets
- Safe Tool Execution
MCP Applications
- MCP Data Assistant
- MCP Document Assistant
- MCP Automation Assistant
Industry Updates & New Features
- MCP Ecosystem Updates
Agentic AI & LangGraph
Introduction to Agentic AI
- What is an AI Agent?
- Agents vs Chatbots
- Agent Architecture
Agent Components
- Goals and Planning
- Tools and Actions
- Memory and State
- Agent Observability
LangGraph Fundamentals
- Introduction to LangGraph
- Nodes, Edges, and State
- Building Agent Workflows
- Conditional Routing
Agent Workflows
- Single-Agent Workflows
- Multi-Step Agents
- Human-in-the-Loop Workflows
- Agent Memory and Checkpoints
Multi-Agent Systems
- Multi-Agent Architecture
- Supervisor Agent
- Specialist Agents
- Agent Communication
Agent Evaluation
- Testing Agent Workflows
- Debugging Agent Failures
- Cost and Performance Optimization
- Agent Monitoring
Industry Updates & New Features
- Agentic AI Trends and Frameworks
Guardrails, Evaluation & AI Security
Introduction to AI Guardrails
- Why Guardrails are Needed
- AI Risks and Failure Modes
- Guardrail Architecture
Input Guardrails
- Prompt Injection Detection
- Sensitive Data Detection
- Content Moderation
Output Guardrails
- Structured Output Validation
- Hallucination Detection
- Response Safety Checks
- Citation Validation
Guardrails Frameworks
- Guardrails AI
- NeMo Guardrails
- Pydantic AI Validation
- Custom Guardrail Rules
LLM Evaluation
- Evaluation Metrics
- Test Datasets
- RAG Evaluation
- Agent Evaluation
Production AI Security
- Authentication and Authorization
- API Key and Secret Management
- Logging and Audit Trails
- Responsible AI Deployment
Industry Updates & New Features
- AI Security and Guardrails Trends
Project Phase 1: LLM Chatbot Project
Project Foundation
- Business Problem and Project Roadmap
- LLM Application Architecture
Chatbot Development
- API Setup and Model Integration
- Prompt Design
- Conversation Memory
- Structured Responses
Application Delivery
- Building the User Interface
- Error Handling and Logging
- Testing and Documentation
- Final Project Presentation
Project Phase 2: RAG Document Assistant Project
Project Foundation
- Business Problem and RAG Architecture
- Document Source and Data Design
Knowledge Base Development
- Loading and Cleaning Documents
- Chunking and Metadata
- Embeddings and Vector Database
- Retrieval Pipeline
RAG Application Development
- RAG Chatbot Development
- Citations and Source Validation
- RAG Evaluation
- RAG Optimization
Project Delivery
- Guardrails and Security
- Application Deployment
- GitHub Documentation
- Final Project Presentation
Project Phase 3: Agentic AI & MCP Project
Project Foundation
- Business Problem and Agent Architecture
- Defining Agent Roles and Tools
MCP Tool Development
- Building MCP Server
- Creating Database and API Tools
- Connecting MCP Tools to LLM
- Tool Permissions and Security
Agent Development
- Building LangGraph Workflow
- Adding Agent Memory and State
- Multi-Agent Collaboration
- Human Approval Workflow
Testing and Guardrails
- Agent Testing and Debugging
- Input and Output Guardrails
- Agent Evaluation and Monitoring
- Cost and Performance Optimization
Project Delivery
- Deploying the Agent Application
- GitHub Documentation
- Final Agent Project Presentation
Unlock with Subscription
Upgrade to Prime Membership to gain access to premium content and unlock a world of exclusive fully animated courses, interview problems, and more!
Projects
Apply what you learn by building real-world projects from this specialization.
AI Customer Support Chatbot
Build an intelligent customer support chatbot using LLMs with context-aware multi-turn conversations.
Document Q&A System
Create a RAG-based Q&A system that answers questions from uploaded documents using Gen AI.
Agentic Workflow Automation
Design an autonomous AI agent that orchestrates multi-step tasks using tool-use and planning.