Learn to design the next generation of AI systems. Explore the architectures and strategies behind autonomous agents that solve complex, real-world problems.
4.5
41 Lessons
2 Breakout Sessions
6h
Updated this week
Join 3 million developers at
Join 3 million developers at
LEARNING OBJECTIVES
- Differentiate AI agents from traditional models by understanding their autonomous capabilities in perception, reasoning, and action.
- Analyze core components of AI agent architecture, including decision-making models, interaction tools, and behavioral instructions.
- Integrate perception, reasoning, memory, and actions to create coherent, dynamic AI agents capable of multi-step tasks.
- Apply orchestration patterns to manage agent behavior in single and multi-agent systems, utilizing frameworks like LangChain and AutoGen.
- Design trustworthy AI agents by implementing guardrails and human oversight mechanisms to ensure safe and responsible operation.
- Evaluate challenges in agentic AI systems and apply design strategies to build resilient, scalable, and effective agents.
KEY OUTCOMES
Design Autonomous AI Agents
Create AI agents that autonomously perceive, reason, and act in complex environments, enhancing their effectiveness in real-world applications.
Implement Robust Agent Architectures
Architect scalable AI systems by integrating core components that support dynamic, multi-step task execution and adaptability.
Orchestrate Multi-Agent Collaboration
Manage interactions between multiple AI agents using orchestration patterns to improve task efficiency and user experience.
Ensure Safe AI Operations
Design and implement safety mechanisms that maintain user trust and prevent risky actions in autonomous AI systems.
Learning Roadmap
1.
Agent Design Fundamentals
Agent Design Fundamentals
Learn core AI agent components, architecture, and how they perceive, reason, and act. Master orchestration, safety, and key design challenges.
2.
Multi-Agent Conversational Recommender System (MACRS)
Multi-Agent Conversational Recommender System (MACRS)
Explore MACRS, a multi-agent system for goal-directed conversational recommendations. See how it plans, uses reflection, and achieves superior performance.
3.
Nvidia Eureka Learning Agent
Nvidia Eureka Learning Agent
6 Lessons
6 Lessons
Dive into Eureka, an LLM-powered agent that autonomously designs and refines RL reward functions.
4.
Implementing a Eureka-Like Reward Learning Agent with Google ADK
Implementing a Eureka-Like Reward Learning Agent with Google ADK
5 Lessons
5 Lessons
Implement a Eureka-like reward learning system using ADK: generate, evaluate, select, reflect, and iterate reward functions end-to-end.
6.
Designing an AI Agent for Generating LLM Pipelines
Designing an AI Agent for Generating LLM Pipelines
4 Lessons
4 Lessons
Explore ChainBuddy’s innovative solutions for efficient LLM evaluation and workflow generation.
7.
Designing a Web Agent
Designing a Web Agent
5 Lessons
5 Lessons
Explore the development of advanced multimodal web agents for enhanced task performance.
8.
Designing a Multimodal-LLM Agent for Multi-Object Diffusion
Designing a Multimodal-LLM Agent for Multi-Object Diffusion
4 Lessons
4 Lessons
Explore MuLan's innovative approach to enhancing text-to-image generation through interactive, multi-step processes.
12.
Appendix: Free Reference Guides and Cheatsheets
Appendix: Free Reference Guides and Cheatsheets
3 Lessons
3 Lessons
A consolidated reference section covering core terminologies, architecture cheatsheets, and real-world application frameworks for AI agent design.
Certificate of Completion
Showcase your accomplishment by sharing your certificate of completion.
Complete more lessons to unlock your certificate
Developed by MAANG Engineers
ABOUT THIS COURSE
Agentic system design is rapidly redefining how modern AI systems are built, moving from single-model interactions to autonomous, multi-step systems that can reason, plan, and act. As large language models evolve, the real challenge is no longer just using them, but orchestrating them into reliable, goal-driven agents that operate safely and effectively in real-world environments.
I built this course from my work in adaptive AI and intelligent systems, where designing autonomous behavior requires more than model accuracy. It demands structured reasoning, control, and safety. A recurring pattern I observed was that teams could experiment with LLMs, but struggled to design cohesive agentic systems that could handle ambiguity, coordinate tasks, and remain aligned with user intent. This course is designed to bring that structure.
You will study real-world examples, including the Multi-Agent Conversational Recommender System (MACRS), NVIDIA’s Eureka for reward generation, and advanced agents navigating live websites and creating complex images. Drawing on insights from industry deployments and cutting-edge research, you will gain the foundational knowledge to confidently start designing your agent-based systems.
Engineers and researchers are already using these patterns to build next-generation AI systems. If you want to design agents that go beyond prompts and into action, this is where to begin.
ABOUT THE AUTHOR
Khayyam Hashmi
Computer scientist and Generative AI and Machine Learning specialist. VP of Technical Content @ educative.io.
Trusted by 3 million developers working at companies
A
Anthony Walker
@_webarchitect_
E
Evan Dunbar
ML Engineer
S
Software Developer
Carlos Matias La Borde
S
Souvik Kundu
Front-end Developer
V
Vinay Krishnaiah
Software Developer
Built for 10x Developers
No Passive Learning
Learn by building with project-based lessons and in-browser code editor
Personalized Roadmaps
The platform adapts to your strengths & skills gaps as you go
Future-proof Your Career
Get hands-on with in-demand skills
AI Code Mentor
Write better code with AI feedback, smart debugging, and "Ask AI"
MAANG+ Interview Prep
AI Mock Interviews simulate every technical loop at top companies
Free Resources
