AI/ML engineers, software developers, data scientists, and technical professionals interested in building autonomous AI systems

Familiarity with Python programming and a basic understanding of APIs

Course Outline:

Day 1 – Foundations of Agentic AI

Learning goals:

1. Understand what “agentic AI” means in practice
2. Grasp the OpenAI SDK as the foundation of agent behavior
3. Write agents that reason and act

Core topics:

1. The Agentic Model: think → act → observe → adjust
2. Degrees of Autonomy
3. Agentic AI Applications
4. Decomposing a Task for Agentic AI
5. Common Design Patterns:
6. ReAct
7. Plan–Execute
8. Reflection
9. Overview of the OpenAI SDK: Assistants, messages, and functions
10. The anatomy of an agent loop (reason–act–observe)
11. Practical exposure to tools (retrieval, code execution, function calling)
12. Building an agent that uses a tool (e.g., web search, MCP)

Hands-on labs:

1. Create a reasoning agent using OpenAI’s SDK.
2. Add one tool: function or API call.
3. Observe and explain its decision steps.

Day 2 – Building Agentic Behavior: Memory, Tools, and Autonomy

Learning goals:

1. Extend agents with memory, multiple tools, and goal-directed reasoning
2. Understand the principles of evaluation, reliability, and safe autonomy
3. Learn to chain decisions and responses within the SDK

Core topics:

1. State and memory: how agents remember context and past actions
2. Tool orchestration: context-aware selection
3. Error handling and guardrails: keeping autonomy reliable
4. Evaluation and logging: traces and workflow analysis
5. Integrating with external data (e.g., retrieval-augmented generation, APIs)

Hands-on labs:

1. Build an assistant that plans a multi-step task (e.g., data analysis, research)
2. Add short-term memory (context tracking) and simple reasoning traces
3. Evaluate success and failure cases

Day 3 – Multi-Agent Systems: Coordinating Workflows

Learning goals:

1. Consolidate understanding of SDK-level agency through a project
2. Understand the conceptual leap to multi-agent systems
3. Get a guided preview of LangGraph and its design philosophy

Core topics:

1. Planning a practical agent system end-to-end
2. Introduction to LangGraph: graphs as stateful workflows for agents
3. Nodes, edges, and control flow: the logic of orchestration
4. How LangGraph builds on the OpenAI SDK
5. LangGraph for persistent agents, collaboration, workflow management

Hands-on labs:

1. Build and coordinate multiple SDK-based agents
2. Guided demo: LangGraph workflow, coordinating two agents (e.g., “researcher” and “summarizer”).
3. Discuss design trade-offs and extensibility

Training material provided: Yes (Digital format)