Intermediate 10 hours English Course CertificateFREE
Our recommendation
Andrew Ng's free, vendor-neutral introduction to agentic AI. Across five modules it builds the four core agent design patterns — Reflection, Tool Use, Planning, Multi-Agent Collaboration — from first principles in Python before touching frameworks. It's a foundations course, not a production deep-dive, which makes it an ideal first step into agents before something framework-heavy.
Good for: Developers who want a clear, free, framework-neutral first course on AI agents.
Less suitable if: You already know the patterns and want deep, framework-specific production skills.
Skills you'll gain
AI agentsAgent design patternsTool callingPlanningMulti-agent systemsPython
Is this course right for you?
A good fit if you…
You're new to building agents
You want to understand patterns, not just call a framework
You like vendor-neutral foundations
Consider something else if you…
You want production-grade, framework-specific depth
You already know agent design patterns
You want a long, comprehensive program
Requirements: Working PythonBasic LLM-API familiarity helps
Realistic time: 5 modules, roughly a couple of hours each — about 10 hours, self-paced
About this course
Agentic AI is Andrew Ng's course on building AI systems that take action through iterative, multi-step workflows. Across five modules it teaches the four agentic design patterns — Reflection, Tool Use, Planning and Multi-Agent Collaboration — building each from first principles in Python before layering on frameworks, so you understand what's happening under the hood.
What you'll learn
Understand the four agentic design patterns
Build Reflection, Tool-Use, Planning and Multi-Agent workflows in Python
Implement each pattern from first principles before using frameworks
Judge when an agentic approach is (and isn't) the right tool
This course includes
10h
On-demand video
Yes
Certificate
Yes
Mobile access
English
Language
What it costs
Free on DeepLearning.AI's own platform, including the completion certificate. You may spend a little on model API calls while building.
Comparison · LBS
Compare alternatives for Agentic AI
Same topic, different options. We surface the trade-offs others hide so you can pick the course that actually fits your time, budget, and goals.
DEDeepLearning.AI
Agentic AI
Price
Free
Free
Duration
10 hrs
Level
Intermediate
Certificate
Course Certificate
UDUdemy4.7(36,179)
AI Engineer Core Track: LLM Engineering, RAG, QLoRA, Agents
A DeepLearning.AI completion certificate — a credible learning signal (Andrew Ng's brand), though as a foundations course it's a starting point rather than a job qualification on its own.
Instructor
AN
Andrew Ng
DeepLearning.AI instructor
Andrew Ng co-founded Coursera and Google Brain and founded DeepLearning.AI. He's known for making hard AI ideas approachable — the reason his courses are so often the recommended starting point.
About this provider
DE
DeepLearning.AI
Andrew Ng's education company — practical, largely-free courses and short courses on generative AI, agents, and machine learning, with a vendor-neutral, build-first style.
For a free, framework-neutral introduction to agents, yes — it teaches the core design patterns clearly from first principles. It's a foundation, so pair it with a framework-specific course for production depth.
It's an accessible introduction but assumes working Python. It's one of the better first courses on agents.
It focuses on the patterns in Python first, then touches frameworks. For deep framework skills, follow it with a dedicated course (e.g. LangGraph or Ed Donner's Agentic Track).
Yes — free on DeepLearning.AI's platform, certificate included.