Courses
AI Courses#
Editorially curated courses from the best AI training platforms — each selected and annotated by our editors with guidance on who should take it and why.
These are external courses hosted on platforms like Anthropic Academy, DeepLearning.AI, NVIDIA DLI, and others. We don’t create courses — we curate the best ones and explain how they connect to the documentation and learning paths in this knowledge base.
Courses are external training programs (video, hands-on labs, certifications) hosted on other platforms.
AI Fundamentals
AI for Everyone
Andrew Ng’s definitive non-technical introduction to AI — the single best starting point for anyone who wants to understand what AI can and cannot do without writing a line of code. Covers AI terminology, what machine learning is, what data it needs, and how to spot opportunities for AI in your organization. Over 4 million enrollments make this the most popular AI course ever created. Take this before any other course if you’re new to AI.
Introduction to AI
Created by the University of Helsinki, this is the most accessible and comprehensive non-technical AI course available. With over 2 million signups from 170+ countries and a 4.8/5 rating, it covers AI concepts, machine learning, neural networks, and societal implications through interactive exercises. The 30-hour estimate is generous — most complete it in 15-20 hours. Unlike Andrew Ng’s course which is video-based, this is primarily text-based with embedded exercises, making it excellent for self-directed learners who prefer reading to watching.
Introduction to Generative AI
A 30-minute micro-course that explains what generative AI is, how it works, and how it differs from traditional machine learning. Google’s concise format makes this the fastest on-ramp to understanding LLMs — take this if you need a quick conceptual foundation before diving into provider-specific content. Covers transformer architecture at a conceptual level without code.
Generative AI Explained
NVIDIA’s no-code introduction to generative AI, designed for anyone regardless of technical background. Covers what generative AI is, how large language models work at a conceptual level, and the applications transforming industries. Shorter and more focused than Elements of AI or AI for Everyone — take this for NVIDIA’s GPU-centric perspective on why generative AI requires different infrastructure than traditional software.
Practical Deep Learning for Coders
Jeremy Howard’s legendary top-down deep learning course — you build working models in lesson 1 and learn theory as needed. This course has produced alumni at Google Brain, OpenAI, Adobe, and Tesla. The teaching philosophy is radical: start with practical results, then go deeper. Covers computer vision, NLP, tabular data, and deployment using PyTorch, fastai, and Hugging Face Transformers. If you learn by doing rather than by theory, this is the best deep learning course available anywhere.
Intro to Machine Learning
The fastest hands-on introduction to machine learning — 3 hours from zero to building your first model. Kaggle’s browser-based notebooks mean no setup required, and the 30 free GPU hours per week let you experiment immediately. Covers decision trees, model validation, underfitting/overfitting, and random forests with real datasets. Take this if you want to get your hands dirty with ML code in an afternoon, not a semester.
Azure AI Fundamentals (AI-900)
Microsoft’s structured learning path for the AI-900 certification — covers AI workloads, machine learning principles, computer vision, NLP, and generative AI on Azure. The most enterprise-oriented AI fundamentals course available, designed for professionals who need to understand AI in the context of cloud services and business applications. Each module has knowledge checks and the path directly prepares you for the AI-900 certification exam.
Prompt Engineering & AI Fluency
AI Fluency: Framework & Foundations
Anthropic’s foundational AI fluency course teaching the 4D Framework — Delegation, Description, Discernment, and Diligence — for effective AI collaboration. Co-created with university professors (UCC, Ringling College), this goes beyond prompt engineering to teach a systematic approach for working with AI effectively, efficiently, ethically, and safely. The 4D Framework provides a mental model that transfers across any AI tool, not just Claude. Start here before the audience-specific fluency courses.
AI Fluency for Educators
Applies the 4D AI Fluency Framework specifically to teaching and institutional strategy. Designed for faculty, instructional designers, and educational leaders who need to integrate AI into curricula responsibly. Covers practical scenarios: classroom policies, assignment design, academic integrity, and helping students develop AI skills. Take this after the Framework & Foundations course for education-specific applications.
ChatGPT Prompt Engineering for Developers
The most popular prompt engineering course available — taught by Isa Fulford (OpenAI) and Andrew Ng. In just one hour, covers prompting best practices, iterative prompt development, summarizing, inferring, transforming, and expanding text. Despite the OpenAI branding, the techniques apply to any LLM. The concise format makes it the ideal first technical introduction to prompt engineering before exploring provider-specific approaches in Anthropic’s and OpenAI’s documentation.
Claude 101
Learn how to use Claude effectively for everyday work tasks. Covers Claude’s core features, capabilities, and resources for more advanced learning. This is the official product training course for Claude — take it to understand Claude’s strengths and how to get the most out of it before diving into API-level courses or the developer track.
Introduction to Responsible AI
Google’s concise introduction to responsible AI practices — covers fairness, interpretability, privacy, and security in AI systems. At just 30 minutes, this is the fastest way to understand the principles that should guide any AI deployment. Pairs well with the AI Safety learning paths in this knowledge base for a more comprehensive view of safety across providers.
Building AI Applications
Building with the Claude API
The most comprehensive free course on building with Claude’s API — 21 lessons covering everything from basic API calls to tool use, structured outputs, and agent patterns. This is Anthropic’s flagship developer course and the definitive companion to the Claude API documentation in this knowledge base. If you’re building production applications with Claude, this course provides the hands-on practice that documentation alone cannot. Take this alongside the Claude API Essentials learning path.
Introduction to Model Context Protocol
The only structured course on MCP available anywhere — Anthropic Academy’s introduction covers MCP architecture, the client-server model, tools/resources/prompts primitives, and building your first MCP server. This is the video/hands-on complement to the MCP documentation in this knowledge base. The MCP Fundamentals learning path provides the documentation reference; this course provides the guided walkthrough with exercises.
MCP: Advanced Topics
Advanced MCP patterns including complex tool implementations, resource management, transport configuration, authentication, and production deployment. This is the second course in Anthropic’s unique MCP sequence — no other provider offers this depth of MCP training. Pairs with the Building MCP Servers learning path for a complete MCP education: the course provides guided exercises, the path provides documentation deep-dives.
Introduction to Agent Skills
Learn to build structured, reusable capabilities for Claude-based agents using the Agent Skills framework. Covers skill design, packaging, tool orchestration, and deployment patterns. This is Anthropic’s bridge between basic API usage and production agent development — take it after the Claude API course and before diving into the Agent SDK Deep Dive learning path.
Claude Code 101
Quick introduction to Claude Code — Anthropic’s agentic coding tool that lives in your terminal. Covers setup, basic usage, and key features. This is the video companion to the Claude Code Mastery learning path: the course gets you started quickly, the path provides comprehensive documentation coverage.
Claude Code in Action
Advanced Claude Code workflows — hooks, sub-agents, headless mode, and integration patterns. Builds on Claude Code 101 with real-world usage patterns. Pairs with the SDD Fundamentals learning path for a complete spec-driven development workflow using Claude Code.
LangChain for LLM Application Development
Harrison Chase (LangChain CEO) and Andrew Ng’s one-hour introduction to building LLM applications with LangChain. Covers chains, memory, prompts, and agents. The fastest way to understand what LangChain does and whether it’s the right framework for your use case. Pair with the RAG from Scratch learning path to go deeper into retrieval-augmented generation patterns.
Functions, Tools and Agents with LangChain
Deepens the LangChain introduction with focus on function calling, tool use, and agent patterns — the building blocks of agentic AI applications. Covers OpenAI’s function calling API, LangChain tool abstractions, and conversational agents. Take this after the LangChain intro to understand how agents actually work under the hood.
Building Agentic RAG with LlamaIndex
Combines RAG with agentic patterns using LlamaIndex — covering router queries, tool retrieval, and multi-document agents. This goes beyond basic RAG (query → retrieve → generate) to show how agents can dynamically choose retrieval strategies and combine multiple data sources. Take this after understanding basic RAG concepts from the RAG from Scratch learning path.
Multi AI Agent Systems with crewAI
Hands-on introduction to multi-agent systems using CrewAI — covers role-based agent design, task delegation, inter-agent communication, and workflow orchestration. Taught by Joao Moura (CrewAI founder). The practical companion to the Multi-Agent Systems learning path: the course teaches you to build crews, the path provides comprehensive documentation across 8+ frameworks.
NLP Course
Hugging Face’s comprehensive NLP course — covers tokenizers, transformers, fine-tuning pretrained models, and the Hugging Face ecosystem (Datasets, Tokenizers, Transformers, Accelerate). The definitive open-source-first approach to NLP: everything runs on Hugging Face infrastructure with free GPU access. If you’re building with open models rather than proprietary APIs, start here.
LLM Course
Hugging Face’s newer LLM-specific course covering the full stack: using LLMs, building LLM applications, fine-tuning, and deploying. More focused on the modern LLM workflow than the NLP course. Includes RAG, quantization, and model evaluation. Take this for an open-source-first perspective on the same topics covered by the provider-specific learning paths in this knowledge base.
Agents Course
Hugging Face’s comprehensive agents course — covers agent fundamentals, tool use, ReAct pattern, multi-agent systems, and building production agents with open-source models. The open-source counterpart to Anthropic’s agent courses: where Anthropic teaches you to build agents with Claude, Hugging Face teaches you to build agents with any open model. Essential if you’re evaluating open vs. proprietary agent architectures.
Specialized & Advanced
Fundamentals of Deep Learning
NVIDIA’s flagship deep learning workshop — 8 hours of hands-on training with GPU cloud servers included. Covers neural network fundamentals, CNNs, data augmentation, and deployment. The unique selling point is access to NVIDIA’s cloud GPU infrastructure during the course, so you train real models without setting up your own hardware. The most hardware-focused deep learning course available, taught from the perspective of the company that makes the chips.
Fine-Tuning Large Language Models
One-hour introduction to when and how to fine-tune LLMs — covers the decision framework (prompt engineering vs. fine-tuning vs. RAG), data preparation, training process, and evaluation. The fastest way to understand whether fine-tuning is right for your use case before committing engineering resources. Pairs with the Fine-Tuning Across Providers learning path for provider-specific implementation details.
Evaluating and Debugging Generative AI Models
Covers evaluation metrics, debugging techniques, and systematic testing for generative AI applications using Weights & Biases. The practical companion to the Evaluation & Testing learning path — the course provides hands-on practice with evaluation tools, while the path covers the full evaluation landscape across providers.
Reinforcement Learning Course
The most accessible free reinforcement learning course available — covers Q-learning, deep Q-networks, policy gradient methods, PPO, and RLHF (reinforcement learning from human feedback). RLHF is the technique that makes ChatGPT and Claude behave helpfully — understanding it gives you insight into how modern LLMs are trained and aligned. Unique coverage that no other free platform provides at this depth.
Deep Learning Specialization
Andrew Ng’s legendary 5-course deep learning specialization — the gold standard for understanding neural networks from the ground up. Covers neural network foundations, hyperparameter tuning, CNNs, sequence models, and attention mechanisms. This is the theoretical foundation that makes everything else in this knowledge base make sense. Not a short commitment (60+ hours), but if you want to truly understand how LLMs work under the hood, this is the investment.
Intro to Deep Learning
Kaggle’s hands-on deep learning micro-course — 4 hours covering neural networks, stochastic gradient descent, overfitting, dropout, and batch normalization. Shorter and more practical than Coursera specializations, with browser-based notebooks that run immediately. The fastest path from ‘I understand basic ML’ to ‘I can build neural networks’ — take this before investing in longer courses.
AI for Business & Leadership
AI Capabilities and Limitations
A concise introduction to what AI can and cannot do — the companion course to the AI Fluency Framework. Explains the machine properties (how AI actually works) that the 4D Framework competencies respond to. Essential for product managers and business leaders who need to understand AI capabilities at a conceptual level before making product decisions. Pairs with the AI Landscape for Product Leaders learning path.
Claude with Amazon Bedrock
Learn to deploy Claude through AWS Bedrock — covers provisioned throughput, fine-tuning, and enterprise deployment patterns. Essential for teams evaluating how to access Claude in an enterprise AWS environment. This is the deployment-focused complement to the API-focused courses: the API course teaches you how to call Claude, this course teaches you how to run Claude in your cloud infrastructure.
Claude with Google Cloud's Vertex AI
Learn to deploy Claude through Google Cloud’s Vertex AI — covers model garden access, API integration, and enterprise deployment patterns. The Google Cloud counterpart to the Bedrock course. If your organization uses GCP, this is the path to accessing Claude within your existing cloud infrastructure. Useful for the AI Vendor & Platform Evaluation learning path’s deployment topology assessment.
AI Fluency for Nonprofits
Applies AI fluency concepts specifically to nonprofit contexts — fundraising, program delivery, volunteer management, and impact measurement. Addresses the unique constraints nonprofits face: limited budgets, data sensitivity, and mission alignment. Take this after the Framework & Foundations course for sector-specific applications.
Generative AI Foundations
AWS’s free introduction to generative AI — covers foundation models, training approaches, and how generative AI fits into the AWS ecosystem. Provides the AWS perspective on AI infrastructure, which complements the Anthropic and Google viewpoints in this knowledge base. Useful for teams evaluating Bedrock as their AI deployment platform.
Building AI
The practical follow-up to Introduction to AI — bridges conceptual understanding to hands-on AI development. Covers machine learning algorithms, neural networks, and AI project planning with optional Python exercises. Designed for people who completed the intro course and want to go deeper without committing to a full computer science curriculum. The Python exercises are optional, making it accessible to non-developers who want to understand the mechanics.
Certification Programs
Machine Learning Specialization
Andrew Ng’s updated Machine Learning course with Stanford — the modern successor to the original Coursera ML course that launched the online AI education movement. Three courses covering supervised learning, advanced algorithms, and unsupervised learning using Python and TensorFlow. The most rigorous free ML foundation available, with the Stanford brand adding credential weight. If you want one certification that signals ML competence, this is it.
AWS Certified AI Practitioner
AWS’s foundational AI certification — validates understanding of AI/ML concepts, generative AI, and responsible AI within the AWS ecosystem. The training materials are free; only the exam costs $150. This is the most accessible cloud AI certification available and carries weight in enterprises that use AWS. Good for PMs and technical leaders who want a formal credential demonstrating AI literacy.
Google Cloud ML Engineer Learning Path
Google Cloud’s professional ML certification path — the most technically rigorous cloud AI certification available. Covers ML model development, MLOps, deployment, and monitoring on Google Cloud. Includes hands-on labs with Vertex AI, BigQuery ML, and TensorFlow. The learning path is free; certification exam is $200. Requires significant ML experience — this is not a beginner credential.