AI Agents for Beginners: Build Agents in Python & OpenAI

Name: AI Agents for Beginners: Build Agents in Python & OpenAI
Rating: 4.6 (160 reviews)

Build Real AI Agents with Tools, Memory, Handoffs, & Guardrails Using OpenAI Agents SDK & Python.

Created byProf. Ryan Ahmed, PhD, MBA | 1M+ Students | #1 Best Selling AI Courses

Last updated 12/2025

English

What you'll learn

Build AI agents in Python using OpenAI Agents SDK with Memory and Tools.
Build a travel planner AI Agent that creates an itinerary based on user preferences.
Inspect the agent’s behavior using traces on the OpenAI API platform.
Master best practices in creating Autonomous AI Agents
Master the art of Prompt Engineering & Setting Up Agent Instructions
Understand the Key components of an Effective AI Agent System Prompt (Context, Instruction, Input, & Output Indicator)
Test AI agents and watch it run using the Runner class
Design & build a personal finance AI agent with memory that can recall user preferences, past tasks, & ongoing conversations to deliver personalized experiences
Integrate SQLite-based session storage to enable persistent memory for agents
Test and compare agent behavior before and after adding memory to evaluate improvements in context retention.
Build AI agents that integrate built-in tools (like Code Interpreter) and custom FunctionTools for real-time search & data retrieval
Combine search, memory, and decision-making to run a full end-to-end AI agent workflow.
Build a manager function to orchestrate multi-agent workflows from input to final deliverable.
Implement agent collaboration by passing outputs from one agent to another in a structured workflow.
Create modular AI agents (Researcher, Analyst, Writer) with specialized roles for information gathering, analysis, and reporting.
Implement guardrails to enforce boundaries, such as preventing responses on restricted topics (e.g., politics).
Build handoff mechanisms that transfer context and inputs smoothly between agents
Create a tool as an agent by wrapping an autonomous agent behind a function-tool interface, allowing it to be invoked seamlessly by other agents.

Course content

6 sections • 49 lectures • 4h 31m total length

Watch Your First AI Agent Come to Life7:04
Course Outline, Key Learning Objectives, & Success Tips9:17
Download the Course Materials0:01

Introduction to AI Agents12:04
Build your first AI agent in Python using the OpenAI agents SDK, then expand to memory, tools, and a team of agents to plan a travel itinerary.
OpenAI API Setup12:04
Configure Agent Instructions & Best Practices9:48
learn to build and run your first ai agent with the openai agents sdk, mastering prompt engineering and a system prompt as a detailed job description.
Configure & Run the AI Agent6:39
Practice Opportunity Question: Configure AI Agent & Change Model (LLM)1:21
Practice Opportunity Solution: Configure AI Agent & Change Model (LLM)4:23
Testing Agent Memory & Track API Traces8:47
Practice Opportunity Question: Develop New AI Agent1:52
Practice Opportunity Solution: Develop New AI Agent5:46

Project Introduction: Building AI Agents with Tools6:28
Set up OpenAI and Tivoli API keys, define a Tivoli search function as a tool, and build an AI agent that uses real-time search and a code interpreter.
Tavily Search API Setup4:56
Build and Configure Tool for the Agent11:03
Practice Opportunity Question: AI Agents Tools0:40
Practice Opportunity Solution: AI Agents Tools1:22
Build and Run AI Agents with Tools7:36
Practice Opportunity Question: Running AI Agents with Tools0:56
Practice Opportunity Solution: Running AI Agents with Tools2:41
Using Built-In OpenAI Tools10:53

Project Introduction: Build a team of Agents6:35
Setup APIs and Tools3:03
Configure the first Two Agents6:58
Configure two ai agents—the researcher and the analyst—using a search tool to produce concise research summaries and an analysis of trends, risks, and insights.
Practice Opportunity Question: Run Both AI Agents1:04
Practice Opportunity Solution: Run Both AI Agents2:23
Learn to run a researcher agent to summarize electric vehicle battery data and pass it to an analyst agent for a concise EV market analysis, including lithium iron phosphate.
Configure the third Agent4:00
Practice Opportunity Question: Changing Agent Instructions1:05
Rewrite the writer's agent instructions so outputs are generated entirely in French, and test a concise French report in the next task. Build a manager function to orchestrate these steps.
Practice Opportunity Solution: Changing Agent Instructions1:38
Explore how to reinforce agent instructions, change outputs to French, add emphasis, and ground results in attached documents to improve model performance in a practice opportunity solution.
Full Pipeline Orchestration8:40
Practice Opportunity Question: Build a Team of Agents1:36
Practice Opportunity Solution: Build a Team of Agents9:34
Explore ai agents for beginners by building a multi-agent team in Python and OpenAI to generate creative advertising campaigns, with a creative director, strategist, and tweet copy in a pipeline.

Project Introduction: AI Agents with Guardrails & Handoffs9:58
Design AI agents with guardrails and handoffs, coordinating planner, writer, search, and fundamental analysis tools, plus memory and orchestration via sessions, to generate an executive-ready report.
Setting up Tools & APIs4:13
Best Practices in Adding Guardrails to AI Agents11:41
Practice Opportunity Question: AI Agents with Guardrails0:43
Practice Opportunity Solution: AI Agents with Guardrails3:38
Define a Team of AI Agents4:03
Create Agents As Tools6:52
Learn how to build and connect AI agents as tools, including writer, search, and fundamentals agents, to generate comprehensive reports with executive summaries and follow-up questions.
Practice Opportunity Question: Monitoring Agent Traces0:40
Practice Opportunity Solution: Monitoring Agent Traces4:16
Explore monitoring agent traces and hierarchy in a multi-agent workflow, observing execution time as the writer agent orchestrates searcher and fundamentals analysts.
AI Agents with Handoffs9:49
Practice Opportunity Question: AI Agent as a Tool1:59
Practice Opportunity Solution: AI Agent as a Tool4:37

Requirements

No programming Skills are Required.
You will need a laptop and an internet connection!

Description

In this course, you’ll learn how to build real AI agents in Python using the OpenAI Agents SDK. You’ll understand the core building blocks of modern AI agent systems, including reasoning, memory, tool usage, planning, and guardrails and how these components work together to automate and enhance tasks.

You will also learn how to develop a team of autonomous AI Agents that can work together to achieve a goal. You’ll learn how to inspect and debug agent behaviour using tracing and observability tools, so your agents are not just powerful, but also transparent, testable, and safe.

By the end of this course, you’ll be able to:

Build AI agents in Python using the OpenAI Agents SDK
Understand how agents reason, plan, and execute tasks using system prompts and instructions
Design effective agent system prompts (context, instructions, inputs, and outputs)
Understand how AI agents work under the hood
Use tools, memory, and planning to create more capable, context-aware agents
Design safe agent interactions with guardrails and controlled execution
Compare agent behaviour with and without memory to evaluate context retention

This course is designed for developers and engineers who want a practical, code-first introduction to AI agents. No prior experience with agent architectures or machine learning is required just basic Python knowledge and an interest in building real AI systems that work reliably in practice.

Who this course is for:

Software developers with basic Python skills who want to integrate cutting-edge LLMs and agent frameworks into real-world applications.
Data scientists, ML engineers, and AI researchers who want to build AI Agents.
Entrepreneurs and startup Founders wanting to build AI-powered autonomous agents.
Advanced students and educators looking for practical, hands-on experience with Agentic AI Engineering.
Corporate innovation teams or R&D teams wanting to prototype AI-powered workflows, assistants, and automations.

AI Agents for Beginners: Build Agents in Python & OpenAI

What you'll learn

Explore related topics

Course content

Course Introduction & Key Success Tips3 lectures • 16min

Single AI Agent with No Memory or Tools9 lectures • 1hr 3min

AI Agents with Memory5 lectures • 37min

AI Agents with Tools9 lectures • 47min

Multi-Agent Teams11 lectures • 47min

Agents with Guardrails & Handoffs12 lectures • 1hr 2min

Requirements

Description

Who this course is for: