DeepLearning.AI
Intermediate9h19m

Agentic AI

Instructor: Andrew Ng

DeepLearning.AI

Earn a certificate with PRO · Updated May 8, 2026

  • Intermediate
  • 9h19m
  • 31 Video Lessons
  • 7 Code Examples
  • 8 Graded Assignments PRO
  • Earn a certificate with PRO
  • Updated May 8, 2026
  • Instructor: Andrew Ng
  • DeepLearning.AIDeepLearning.AI
  • Learn more aboutMembership PRO Plan

What you'll learn

  • Build agentic design patterns: reflection, tool use, planning, and multi-agent workflows

  • Integrate AI with external tools: databases, APIs, web search, and code execution

  • Evaluate and optimize AI systems: performance metrics, error analysis, and production deployment

Course recap

PRO

Taught by Andrew Ng, this comprehensive course covers best practices for building agentic AI applications -- workflows where LLM-based apps execute multiple steps to complete tasks. The course emphasizes that the biggest differentiator between effective and ineffective agentic AI builders is the ability to drive a disciplined development process focused on evaluations and error analysis.

Concept map

Concepts in Agentic AI and the courses that connect to themAgentic AIAgentic workflowsReflectionTool CallingPlanningMulti-agent collaborationModel Context ProtocolEvaluations (evals)AI Agentic Design Patterns with AutoGenAI Agentic Design Pattern…AI Agents in LangGraphAgent Skills with AnthropicAgent Skills with Anthrop…A2A: The Agent2Agent ProtocolA2A: The Agent2Agent Prot…Fast LLM Inference with CerebrasFast LLM Inference with C…Building Toward Computer Use with AnthropicBuilding Toward Computer…Building Your Own Database AgentBuilding Your Own Databas…Concepts in Agentic AI and the courses that connect to themAgentic AIAgentic workflowsAgentic workflo…ReflectionTool CallingPlanningMulti-agent collaborationMulti-agent col…Model Context ProtocolModel Context P…Evaluations (evals)Evaluations (ev…

Key concepts

  • Agentic workflowsIterative, multi-step LLM processes that deliver better results than single-shot prompting by incorporating research, revision, and reflection
  • ReflectionHaving an LLM examine its own outputs and iterate, sometimes with external feedback (code execution, web search, pattern matching)
  • Tool CallingGiving LLMs access to functions they can request to call, enabling actions like web search, code execution, database queries
  • PlanningLetting the LLM decide the sequence of actions needed to complete a task rather than hard-coding the workflow
  • Multi-agent collaborationMultiple specialized agents (each an LLM with a specific persona) working together on complex tasks
  • Model Context ProtocolMCP as a standard for giving LLMs access to tools and data sources, reducing M x N integrations to M + N
  • Evaluations (evals)Systematic measurement of agentic workflow performance using objective metrics or LLM-as-judge with rubrics

Why Enroll?

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.

You’ll earn a certificate upon completing the course, recognizing your skills in building agentic workflows.

Instructor

Andrew Ng

Andrew Ng

Founder, DeepLearning.AI; Co-founder, Coursera

Who this course is for

  • Software developers who want to apply AI techniques to build autonomous systems that handle multi-step workflows.

  • Professionals with intermediate-level Python programming skills to be able to follow along with the implementations.

  • Professionals with a basic understanding of large language models and APIs who want to deepen their practical skills.

Course Outline

Agentic AI

Unlock certificates

Elevate your learning experience with Pro

Upgrade to Pro and gain unlimited accomplishments on your resume

Learn More

Learner reviews from other DeepLearning.AI courses

Selami A.

What I loved about the “AI for Everyone” course was the comprehensive coverage of essential AI topics, guided by the expertise of Andrew Ng. The course provided a clear roadmap for initiating and managing AI projects, from project selection to implementation. It also offered insights into building AI teams and introduced the technical tools necessary for AI success

Chris C.

Simple enough to make it easy to understand in spite of being a complex topic, inspiring speaker. Time well spent, and a good fit with “lifelong learning” approach.

Adeel B.

What stood out to me about this course was the clarity and simplicity with which complex AI concepts were explained. The real-life examples and case studies helped me grasp the practical implications of AI in different sectors. The interactive nature of the course made learning engaging and enjoyable.

Krystal L.

I am an educator and looking to incorporate AI into my career and help my colleagues to do the same. The course did a great job explaining AI concepts to people like myself who are just learning about any of this for the first time.

John S.

I took this course purely out of curiosity. After becoming aware of ChatGPT and Midjourney and then taking a short course on engineering the prompts to get the desired result, I became more intrigued with the topic of AI. I found this most helpful with regards to getting an idea about what AI actually is as opposed to what Hollywood conditioned me to believe it might be.

Muhammad S.

Loved the content. It brought simplicity to the complex topic of AI, separated signal from noise, presented a great flow and covered the most relevant topics.

Andrew’s knowledge and passion about the subject of AI was amazing. It was inspiring to listen to him, even via recorded videos. Its really great to be in this era of technology, as it makes it possible to get access to the wealth of knowledge so easily.

Learner Reviews

Frequently Asked Questions

What additional features do I get with the DeepLearning.AI Pro membership for this course?

With a Pro membership, you’ll unlock features that support hands-on, practical learning:

  • Access to quizzes and interactive labs within this course

  • A certificate of completion upon finishing the course

  • The ability to save your progress and resume anytime

  • Access to related learning tracks in the professional certificate series

  • Practice projects that help you apply what you’ve learned

  • Community support and a global network of peers

  • Weekly updates on new AI tools and techniques

If you choose to audit the course for free, you’ll still be able to watch the course videos and participate in the community forum, but you won’t have access to assessments, certificates, or project tools.

Can I take this course at my own pace?

Yes, the course is designed to be self-paced.

How much does the DeepLearning.AI Pro membership cost?

The DeepLearning.AI Pro membership costs $25/mo billed annually and $30/mo billed monthly.

More pricing details are available on the membership page.

Important details:

  • All prices are listed in USD
  • Payments are processed securely via Stripe
  • Taxes may apply depending on your location
Will I receive a certificate when I complete the course?

Yes, if you’re enrolled through the DeepLearning.AI Pro membership and complete the required assessments, you’ll receive a certificate upon completion. If you’re auditing the course for free, a certificate will not be provided.

Stay up to date with AI news!

Keep learning with updates on curated news, courses, and events, as well as Andrew’s thoughts from DeepLearning.AI!

Choose Your Plan

Planning for more users?
Learn More