About the course
Agentic AI represents a new way of building software that leverages LLMs to complete some or all of the steps in complex tasks. Instead of generating single responses to prompts, agentic workflows enable AI to plan multi-step processes, execute them iteratively, and improve outputs through reflection and tool use. This course teaches you to build these sophisticated AI systems from the ground up. You’ll master four design patterns that power agentic AI systems: Reflection: AI critiques its own work and iterates to improve quality—like code review, but automated. Tool Use: Connect AI to databases, APIs, and external services so it can actually perform actions, not just generate text. Planning: Break complex tasks into executable steps that AI can follow and adapt when things don’t go as expected. Multi-Agent: Coordinate multiple specialized AI systems to handle different parts of a complex workflow. The course emphasizes practical implementation using Python, building each pattern from first principles before exploring frameworks, giving you the flexibility to customize AI workflows for your specific needs. You’ll learn to deconstruct business processes into agentic workflows, identifying where human-like iteration and tool interaction can automate complex tasks. Critical evaluation skills are woven throughout—you’ll build robust testing frameworks, conduct systematic error analysis, and optimize systems for production deployment.
The consensus
1 of the 2 reviews we read rated it 3★ or lower, but none of them wrote a comment. This is the most-upvoted review (no upvotes).
“i have very little background in programming(only undertaken basic course in Python),this course helped me understanding the concepts of agent and how to implement them.This course can be good for non technological background persons if they take little effort in learning basic Programming”
Starisk reads the reviews learners voted most helpful, and weights each by the square root of its votes: a review with 80 upvotes counts about five times one with 2. Unvoted reviews are not skipped out of laziness — by this model they carry no evidence that other students endorsed them.
That measures what the most-endorsed reviews say, not “true quality.” The rating distribution above is the whole population, so you can see the sample next to it.
Reviews read on 23 Oct 2026.Read them on Coursera ↗