Learn how to build agentic AI workflows.
We’ve just posted a course on the frequedcamp.org YouTube channel that provides a comprehensive overview of agentic AI, which describes agents as software entities that use LLM to understand the environment, make decisions, and execute actions to achieve specific goals. It explores the important distinction between static workflows and dynamic agentic systems, emphasizing how the LLM acts as the “brain” for decomposing tasks at runtime. Rola Daly, Ph.D., created this course.
Through practical Python demonstrations, this course covers essential system components such as pointers, tools, and memory, while also comparing architectural patterns such as supervisor and swarm. Finally, the session addresses the future of technology by discussing emerging interoperability protocols such as MCP and the shifting paradigms of software development in an AI-driven world.
The sections covered in this course are:
Introduction and background of the speaker
A Brief History of Artificial Intelligence (1940s – Present)
Traditional Machine Learning vs. Generative AI
The three pillars of AI: Algorithms, Data and Compute
Specific task versus general task execution
Defining the spectrum of agency and autonomy
Timeline of Agent Milestones (2017–2026)
What is Generative AI Agent?
Agents vs. Workflows: Dynamic Flows vs. Static Paths
Pros and Cons of Agentic Systems
Patterns and Antipatterns: When to Use Agents
Basic components of an agent
Choosing the Right LLM for Your Agent
Developing an identity with system indicators
Understanding memory: internal, short-term and long-term
Expanding capabilities with tools and functions
Hands-on implementation: From a single LLM call to a Python agent
Adding Memory and History to Your Custom Agent
Building agent with framework (langchain).
The evolving landscape of models and frameworks
Agentic Architectural Pattern: Supervisor vs. Crowd
Case Study: Single Agent vs. Supervisor Architecture
Deep Dive: Swarm Architecture Performance
When choosing a multi-agent system
Interface Protocols: MCP, A2A, and Agui
How to Evaluate Agentic Systems (LLM vs System vs App)
Evaluation Methods: Code-based, LLM-AS-A-Judge, and Human
Current Challenges: Fraud, Cost and Debugging
Database of real world events and AI event
Career Impact: Which Jobs Are Most at Risk?
Software 3.0: The Evolution of Development Paradigms
Weathering the Storm: Strategies for the Future
Beyond the LLMS: Global models and the future of AMI
Suggested resources and closing ideas
View the full course freecodecamp.org YouTube channel (2 hour clock)