Agentic AI

DeepLearning.AI via Coursera

Go to class Write review

Details

Go to class

Provider

Coursera
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Effort

5 weeks, 5 hours a week
Sessions

Self-Paced
Level

Intermediate
Subtitles

English

Found in

Overview

Google, IBM & Meta Certificates – 40% Off

One Coursera Plus subscription covers most Professional Certificates on Coursera.

Unlock All Certificates

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.

Syllabus

Introduction to Agentic Workflows
- This module introduces the core ideas and motivations behind agentic AI workflows and sets the foundation for the rest of the course. You will learn what makes an AI system "agentic" and why we talk about a spectrum of autonomy instead of a rigid binary notion of agents. Through concrete application examples—such as invoice processing, customer-service agents, and research/report-writing systems—you will see how multi-step workflows with LLMs, tools, and optional human review can dramatically extend what is possible beyond single-prompt generation. The module explains task decomposition as a fundamental design skill, shows how to map real-world use cases into discrete, implementable pipeline steps, and highlights the importance of rigorous evaluation and error analysis as the engine of iterative improvement. It also surveys key design patterns—reflection, tool use, planning, and multi-agent collaboration—that you will explore in depth in later modules, and frames the course around shipping reliable, high-impact agentic systems rather than chasing hype.
Reflection Design Pattern
- This module dives into the Reflection design pattern and shows how it can significantly improve the quality and reliability of LLM-based workflows. You will contrast direct (zero-shot) generation with reflection-driven approaches where an LLM critiques and revises its own outputs or responds to external feedback such as error messages or evaluation signals. Through concrete examples—like revising emails, debugging code, and improving chart visualizations—you will see how to construct prompts that ask models to review drafts against explicit criteria and then produce better second versions. The module covers multimodal reflection, where an LLM critiques images or charts, and introduces rigorous evaluations to quantify the gains from reflection, such as improved SQL accuracy in database-query tasks. You will learn how to incorporate runtime signals and external tools into reflection loops, how to design reflection prompts and workflows that outperform simple prompt tuning, and how to recognize where reflection is most beneficial.
Tool use
- This module focuses on tool use and function calling, which allow LLMs to access external capabilities such as APIs, databases, and code execution. You will learn what tools are in the context of agentic workflows and how to expose functions as tools that models can request when needed. The module walks through older marker-based approaches and modern native tool-calling syntax, emphasizing patterns for detecting desired function calls, executing them, and feeding results back to the model. You will implement tools using libraries like AI Suite, explore an email assistant workflow that composes multi-step tool use, and see how code execution can be safely integrated so LLMs can write and run code to solve tasks. Finally, you will be introduced to the Model Context Protocol (MCP), a rapidly growing standard that standardizes access to external tools and data sources and greatly simplifies integrating agentic applications with diverse back-end services.
Practical Tips for Building Agentic AI
- This module provides practical, step-by-step strategies for evaluating, debugging, and improving agentic AI workflows. Building on earlier coverage of evals, you will learn how to perform detailed error analysis by examining traces and failure cases in applications such as invoice processing and customer email response. The module teaches how to distinguish between end-to-end and component-level evaluations, how to isolate and tune specific components (for example, web search in a research agent), and how to use metrics such as precision, recall, and F1 where appropriate. You will explore techniques for optimizing both LLM and non-LLM components, including prompt design, model selection, hyperparameter tuning, and provider swaps, while balancing quality, latency, and cost. Through a structured build-versus-analyze workflow and a 2×2 framework for evaluation types, you will learn how to iterate effectively on agentic systems, prioritize high-impact fixes, and benchmark performance as you move toward reliable, production-ready deployments.
Patterns for Highly Autonomous Agents
- This module explores advanced design patterns for building more autonomous agentic systems that can plan, coordinate, and act with minimal hard-coded control. You will learn planning patterns in which LLMs generate executable plans—either as structured JSON or code—that orchestrate tools and data sources to accomplish complex tasks. Through examples such as retail agents and spreadsheet analytics, you will compare JSON-based plans with code-as-action approaches and understand their trade-offs in flexibility, security, and predictability. The module then turns to multi-agent workflows, where specialized agents with different roles and tools collaborate, and introduces communication patterns such as linear pipelines, hierarchical manager–worker setups, and all-to-all messaging. Finally, it revisits the performance, parallelism, and modularity benefits of agentic workflows, showing how autonomous agents can parallelize sub-tasks and leverage interchangeable components, before concluding with guidance on applying these patterns responsibly in real-world projects.