Practical Exercises

Hands-on activities to reinforce your learning and build real agent components

๐Ÿงช Learning by Doing

Practical application is at the heart of this course. Each module includes hands-on exercises designed to reinforce theoretical concepts and develop your skills in building agentic AI systems.

These exercises range from guided tutorials to open-ended projects, gradually increasing in complexity as you progress through the course. By completing these exercises, you'll build a portfolio of agent components and eventually a complete agentic AI system.

All exercises include starter code, clear instructions, and evaluation criteria to help you assess your progress. Many exercises also offer extension challenges for those looking to deepen their understanding.

Read more about AIVibes' approach to hands-on learning

๐Ÿ’ก Exercise Types

  • Guided Exercises: Step-by-step tutorials with detailed instructions
  • Implementation Tasks: Building specific agent components
  • Analysis Activities: Evaluating existing agent architectures
  • Design Challenges: Creating architectural solutions
  • Integration Projects: Combining components into systems
  • Capstone Project: Building a complete agentic AI system

๐Ÿ”ฌ Module Exercises

Module 1: Foundations

๐Ÿ” Exercise 1.1: Agent Analysis

Analyze and compare different types of AI agents in real-world applications.

Analysis Difficulty: โ˜…โ˜…โ˜†โ˜†โ˜†

๐Ÿงฉ Exercise 1.2: Agent Capabilities Mapping

Map out the capabilities and limitations of different agent architectures.

Design Difficulty: โ˜…โ˜…โ˜…โ˜†โ˜†

๐Ÿ“ Exercise 1.3: Ethical Framework

Develop an ethical framework for agentic AI system development.

Analysis Difficulty: โ˜…โ˜…โ˜…โ˜†โ˜†

Module 2: Architectural Components

๐Ÿ‘๏ธ Exercise 2.1: Perception Module

Implement a basic perception module for processing textual input.

Implementation Difficulty: โ˜…โ˜…โ˜…โ˜†โ˜†

๐Ÿง  Exercise 2.2: Cognition Component

Build a simple reasoning component using rule-based logic.

Implementation Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜†

๐Ÿ”„ Exercise 2.3: Component Integration

Integrate perception and cognition components into a simple agent.

Integration Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜†

Related: Component Architecture Best Practices

Module 3: Data Structures

๐Ÿ•ธ๏ธ Exercise 3.1: Knowledge Graph

Create a knowledge graph for a domain-specific agent.

Implementation Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜†

๐Ÿ“Š Exercise 3.2: Vector Embeddings

Implement vector embeddings for semantic similarity search.

Implementation Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜†

๐Ÿงฎ Exercise 3.3: MDP Modeling

Model a simple decision problem as a Markov Decision Process.

Design Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜…

Module 4: Planning Algorithms

๐Ÿ—บ๏ธ Exercise 4.1: Symbolic Planner

Implement a basic symbolic planning system for an agent.

Implementation Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜†

๐ŸŽฎ Exercise 4.2: Reinforcement Learning

Train a simple RL agent to solve a decision-making problem.

Implementation Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜…

๐Ÿ”€ Exercise 4.3: Hybrid Planning

Design a hybrid planning approach combining symbolic and learning-based methods.

Design Difficulty: โ˜…โ˜…โ˜…โ˜…โ˜