Are you ready to build AI that thinks, acts, and gets things done? In this course, you’ll learn how to design agents that go beyond language generation to reason, take action, and tackle real-world tasks using tools and data.



Fundamentals of Building AI Agents
This course is part of IBM RAG and Agentic AI Professional Certificate

Instructor: Joseph Santarcangelo
Included with
Recommended experience
What you'll learn
Develop AI agents that can reason and perform tasks independently
Implement function calling and chaining to create structured AI workflows
Utilize built-in LangChain agents to analyze data, generate visualizations, and execute database queries
Apply best practices in prompt engineering and tool calling to enhance AI agent performance
Skills you'll gain
Details to know

Add to your LinkedIn profile
6 assignments
See how employees at top companies are mastering in-demand skills

Build your Software Development expertise
- Learn new concepts from industry experts
- Gain a foundational understanding of a subject or tool
- Develop job-relevant skills with hands-on projects
- Earn a shareable career certificate from IBM

There are 3 modules in this course
In this module, you'll discover how tool calling and chaining work together in LangChain to create powerful AI systems. You'll learn to connect language models with external tools and orchestrate these components through structured workflows using LangChain Expression Language (LCEL). You'll gain skills you can use to build systems that perform precise operations while maintaining natural conversational abilities.
What's included
4 videos2 readings2 assignments1 app item3 plugins
In this module, you’ll learn how to manually invoke tools in LangChain by parsing large language model (LLM) outputs, validating inputs, and executing functions. You’ll build a real-world tool calling agent that includes workflows where the LLM suggests tools while you retain full control for processing the query.
What's included
3 videos1 reading3 assignments2 app items2 plugins
In this module, you'll learn how to use LangChain's built-in DataFrame and SQL agents for data analysis and database operations. Discover how these pre-built agents implement natural language interfaces for conversational data analysis, making insights available to users without technical expertise. You'll learn how to build AI-driven applications that convert conversational queries into structured data operations, enhancing usability and decision-making.
What's included
2 videos3 readings1 assignment2 app items2 plugins
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Instructor

Offered by
Explore more from Software Development
Why people choose Coursera for their career




New to Software Development? Start here.

Open new doors with Coursera Plus
Unlimited access to 10,000+ world-class courses, hands-on projects, and job-ready certificate programs - all included in your subscription
Advance your career with an online degree
Earn a degree from world-class universities - 100% online
Join over 3,400 global companies that choose Coursera for Business
Upskill your employees to excel in the digital economy
Frequently asked questions
AI agent development skills are valuable for roles such as Software Developers, Data Scientists, Machine Learning Engineers, AI Developers, AI Engineers, and Automation Specialists.
These positions involve building intelligent systems that use language models to interact with tools, run code, and automate real-world workflows. These are skills that are increasingly in demand across tech-driven industries.
Not at all! If you're already familiar with Python, you're all set. This course teaches you how to create AI agents using LangChain. You won’t need an advanced machine learning background to build real-world, action-oriented AI systems.
Building AI agents goes beyond writing fixed application logic. It focuses on creating intelligent systems that can reason, make decisions, and take action by calling external tools, executing code, and interacting with data. While you still use Python and frameworks like LangChain, the approach includes designing structured workflows using function calling, chaining, and tool orchestration. This enables your applications to respond intelligently and perform tasks autonomously, offering far more flexibility than traditional software.
More questions
Financial aid available,