Key Takeways
-
Learn the fundamentals and applications of key agentic design patterns—Reflection, Tool Use, Planning (ReAct), and Multi-Agent systems—in AI workflows.
-
Gain hands-on experience in developing Python-based agents using state-of-the-art LLMs like Groq for tool-building, reasoning, and coordination.
-
Learn how to combine these design patterns to create modular, extensible, and high-performing autonomous agents.
Who should enroll?
-
Ideal for students seeking practical knowledge of how intelligent agents are designed and deployed using real-world LLM tools.
-
Perfect for AI/ML engineers, product developers, and technical architects looking to integrate agentic workflows into their GenAI applications or research.
About the Instructors
Miguel Otero Pedrido - Founder @ The Neural Maze|ML Engineer
Miguel Otero Pedrido is the founder of The Neural Maze,- a hub for machine learning (ML) projects where concepts are explained step-by-step with code, articles, and video tutorials.
He is a seasoned AI professional with extensive experience in developing and implementing AI solutions across various industries. Miguel has a strong background in machine learning, natural language processing, and computer vision, and has contributed to numerous projects that leverage AI to solve complex problems. Passionate about sharing his knowledge, he has mentored and taught, helping others understand and apply AI technologies effectively.
Course curriculum
-
1
Reflection Pattern
- Implementing Reflection Pattern to evaluate output
- Quiz
-
2
Tool Pattern
- How to build tools from scratch using Python and Groq LLMs
- Quiz
-
3
Planning Pattern
- Building a ReAct Agent from Scratch
- Quiz
-
4
MultiAgent Pattern
- Building a minimalistic multiagent framework
- Quiz
FAQ
-
Why are design patterns important in building AI agents?
Design patterns offer reusable, structured approaches to solving common challenges in agent design—like reasoning, coordination, or decision-making—making development more scalable and modular.
-
What is the Reflection Pattern in Agentic AI, and why is it useful?
The Reflection Pattern enables agents to self-evaluate or critique their responses to improve accuracy, coherence, and alignment with goals—mimicking human reflection loops.
-
How do Tool Patterns enhance an agent’s capabilities?
Tool Patterns allow agents to extend their functionality by interacting with external tools or APIs, enabling complex operations like web scraping, calculations, or API calls beyond native model outputs.
-
Will I receive a certificate upon completing the course?
Yes, the course provides a certification upon completion.
-
What is a ReAct Agent, and how does Planning Pattern apply to it?
ReAct Agent blends reasoning and action by planning next steps based on intermediate results, using a structured loop of “think-act-think” to solve tasks more effectively.