Course Prerequisites:
Basic Understanding of AI Concepts – Familiarity with core AI principles.
Programming Knowledge – Proficiency in Python or similar languages.
Data Analysis Skills – Ability to interpret and manipulate datasets.
Problem-Solving Mindset – Analytical thinking to address AI challenges.
Familiarity with Machine Learning – Understanding basic ML algorithms and techniques.
Modules:
Module 1: Introduction to AI Agents
1.1 Understanding AI Agents
1.2 Anatomy and Ecosystem of AI Agents
1.3 Applications, Misconceptions, and Mini Case Studies
1.4 Case Study: Transforming Customer Support at Acme Retail with AI Agents
1.5 Hands-On Exercise 1: Build a Q&A ChatBot Using Gemini + Prompt + LLM Chain in Flowise Cloud
Module 2: Core Concepts & Types of AI Agents
2.1 Anatomy of an AI Agent
2.2 Classification of AI Agents
2.3 Matching Agents to Use Cases
Module 3: Tools for Non-Coders
3.1 No-code and Visual Agent Platforms
3.2 Tools Overview and Setup
3.3 Start building: “Your First Flow” with n8n
3.4 Case Study: Empowering HR with AI – Building an Onboarding Assistant Without Coding
3.5 Hands-on Exercise
Module 4: Building Simple Agents
4.1 Agent 1: AI-Powered HR Policy Assistant
4.5 Troubleshooting and Validation of AI Agents
4.6 Share Your AI Agent
4.7 Hands-on Exercise 1: Design and Implementation of an AI-Powered Research Assistant using
Module 5: Multi-Tool Agents and Workflow Automation
5.1 Multi-Tool Agent
5.2 Agent Chaining and Workflow Basics
5.3 Managing Agent State: State, Context, and User Journey
5.4 Prompt Engineering for Agents
5.5 Multi-Agent System
5.6 Case Study: Chaining Tools for Smarter Marketing Campaigns
5.7 Hands-on Exercise 1: Automating Order Tracking and Real-Time Notifications using Make.com
Module 6: Integration, Application Mapping & Deployment
6.1 Deploying Agents
6.2 Channel Selection
6.3 Hosting Environment
6.4 Data Integration
6.5 Security Setup
6.6 Monitoring & Updates
6.7 Application Mapping
Module 7: Monitoring, Guardrails & Responsible AI
7.1 Observability Basics
7.2 Performance Evaluation: Key Metrics
7.3 Guardrails: Preventing Misuse & Ensuring Safe Outputs
7.4 Responsible AI
7.5 Mini-Case: Failure and Recovery in Agent Deployments
7.6 Real-world Failures
7.7 Peer Sharing: How to Present and Discuss Agent Logs/Results
Module 7: Capstone Project – Design Your Own Intelligent Agent
8.1 Capstone Project 1: Smart Personal AI Assistant