Skip to content
anythingai.space
+References & Evals·9 min read

Recommended AI Courses & Learning Paths

A curated list of reliable, trusted online courses for AI engineers, ML practitioners, and product teams, chosen for concepts that age well. No fluff, no outdated MOOCs. Providers rename, move, and retire courses, so if a link redirects, follow it to the provider's current version.

Note on code staleness: these courses are curated for their concepts. The framework APIs they use (LlamaIndex, LangChain) churn fast, so notebook code in any recorded course drifts out of date and can fail on a fresh install. Before copy-pasting, run the 30-second currency check in Navigating Framework Churn, and learn the primitives, not the import paths.



Foundation: LLMs & Transformers

CourseProviderCostWhy It's Trusted
Neural Networks: Zero to HeroAndrej Karpathy (YouTube)FreeThe definitive from-scratch series by an OpenAI/Tesla legend. Builds GPT from scratch.
CS324: Large Language ModelsStanfordFreeStanford-quality lecture notes covering LLM fundamentals, scaling laws, alignment.
Generative AI with LLMsDeepLearning.AI + AWS (Coursera)~$50Hands-on intro to LLMs, covering training, fine-tuning, RLHF. By Andrew Ng's team.
Practical Deep Learning for Codersfast.aiFreeBottom-up, code-first approach. Best for engineers who learn by doing.

RAG Pipelines

CourseProviderCostWhy It's Trusted
Building and Evaluating Advanced RAGDeepLearning.AI + LlamaIndexFreeCovers sentence-window retrieval, auto-merging, RAG evaluation with TruLens.
Vector Databases: from Embeddings to ApplicationsDeepLearning.AI + WeaviateFreePractical walkthrough of embeddings, vector stores, and hybrid search.
Building RAG Agents with LLMsNVIDIA Deep Learning InstituteFreeEnterprise-grade RAG with NVIDIA NIM. Covers chunking, reranking, evaluation.
LlamaIndex: Understanding LlamaIndexLlamaIndexFreeOfficial LlamaIndex learning path: short tutorials on agents, workflows, and RAG, plus observability and evaluation. Best for deep RAG pipeline mastery.
RAG Fundamentals (Haystack)deepset / HaystackFreeHands-on tutorials for pipeline-based RAG using the Haystack framework.

Agentic AI & Multi-Agent Systems

CourseProviderCostWhy It's Trusted
AI Agents in LangGraphDeepLearning.AI + LangChainFreeLangGraph by the creators. Covers ReAct, persistence, human-in-the-loop, multi-agent.
Multi AI Agent Systems with crewAIDeepLearning.AI + crewAIFreeOfficial CrewAI course. Covers Crews, Flows, and real-world business automations.
Building Agentic RAG with LlamaIndexDeepLearning.AI + LlamaIndexFreeRouting, tool-calling agents, and multi-document agentic retrieval.
Functions, Tools and Agents with LangChainDeepLearning.AI + LangChainFreeTool-calling, OpenAI function calling, building from scratch.
AI Agentic Design Patterns with AutoGenDeepLearning.AI + Microsoft ResearchFreeMulti-agent patterns: debate, tool use, and code execution agents. AutoGen itself is now in maintenance mode, succeeded by Microsoft Agent Framework (GA April 2026), so take the patterns, not the API.
CS294/194-196: LLM Agents (Berkeley)UC BerkeleyFreeGraduate-level course on LLM agents. Covers memory, planning, safety, evaluation.
Model Context Protocol Associate (MCPA)Linux Foundation / Agentic AI Foundation$250 (exam)A certification, not a course: a proctored, 90-minute multiple-choice exam aligned with MCP spec 2026-07-28, launched September 14, 2026. Security and governance is 24% of it. A vendor-neutral signal, but shipped MCP work still counts for more.

Context & Memory Management

CourseProviderCostWhy It's Trusted
Building Systems with the ChatGPT APIDeepLearning.AI + OpenAIFreeCovers multi-turn conversation state, context management, moderation chains.
Prompt Engineering with Llama 2DeepLearning.AI + MetaFreeShows context window tradeoffs and system prompt management with Llama 2.
Reasoning with o1DeepLearning.AI + OpenAIFreePrompting and planning with reasoning models. The model is older than anything you will deploy, but the ideas map directly onto today's reasoning-effort controls (reasoning.effort on OpenAI, adaptive thinking with an effort setting on Claude).
Mem0 DocumentationMem0 (official)FreeOfficial reference for multi-tier memory in production agents. Mem0 2.x changed the write model (memories are add-only since 2.0) and current releases drop graph drivers, so older tutorials break.

AI Evaluations & Observability

CourseProviderCostWhy It's Trusted
AI Evals For Engineers & PMsHamel Husain & Shreya Shankar (Maven)Paid (cohort)Industry gold standard for AI evals. Used in production at dozens of companies. Our repo's evals guides are based on this course.
Evaluating and Debugging Generative AIDeepLearning.AI + W&BFreeCovers tracing, evaluation with W&B Weave, and experiment tracking.
Quality and Safety for LLM ApplicationsDeepLearning.AI + WhyLabsFreeCovers hallucination detection, toxicity, bias evaluation, and drift monitoring.
LangSmith Evaluation ConceptsLangChainFreeOfficial LangSmith docs are the best hands-on eval reference if you use the LangChain ecosystem. Covers offline and online evaluation.
Arize Phoenix DocsArize PhoenixFreeHands-on tutorials for tracing and evals with Phoenix, which is source-available under the Elastic License 2.0. Dynatrace completed its acquisition of Arize on October 1, 2026 and has said Phoenix remains available.

📖 Also see this repo's companion guides:


Prompt Engineering & Context Engineering

CourseProviderCostWhy It's Trusted
ChatGPT Prompt Engineering for DevelopersDeepLearning.AI + OpenAIFreeThe foundational prompt engineering course. By Isa Fulford & Andrew Ng.
Interactive Prompt Engineering TutorialAnthropic (GitHub)FreeStraight from the Claude team: nine chapters with exercises covering prompt structure, XML tags, separating data from instructions, examples, and avoiding hallucinations. It runs on an older Claude model, but the techniques transfer.
DSPy: Building Optimizable PipelinesStanford NLP (GitHub)FreeNot a course but the DSPy repo's notebooks are the best way to learn programmatic prompting.
Prompt Engineering GuideDAIR.AIFreeComprehensive, community-maintained reference covering all major prompting techniques.

Fine-tuning & Adaptation

CourseProviderCostWhy It's Trusted
Finetuning Large Language ModelsDeepLearning.AI + LaminiFreeCovers LoRA, full fine-tuning, dataset preparation, evaluation. Concise and practical.
Reinforcement Learning from Human FeedbackDeepLearning.AI + AWSFreeDeep dive into RLHF: reward models, PPO, preference datasets.
Hugging Face LLM CourseHugging FaceFreeFormerly the NLP Course. The best free course for fine-tuning transformers with the HF ecosystem (Trainer, PEFT, etc).
How Diffusion Models WorkDeepLearning.AIFreeFor image model fine-tuning (stable diffusion, LoRA for images).

Inference Optimization & MLOps

CourseProviderCostWhy It's Trusted
Machine Learning in ProductionDeepLearning.AI (Coursera)PaidAndrew Ng's course on the production ML lifecycle: deployment patterns, monitoring, and data-centric fixes. The older four-course MLOps specialization now redirects here.
Efficiently Serving LLMsDeepLearning.AI + PredibaseFreeCovers vLLM, PagedAttention, quantization, LoRA serving. Exactly what this guide covers.
vLLM Documentation & TutorialvLLMFreeThe official vLLM docs are the most up-to-date reference for high-throughput serving.

AI Safety & Guardrails

CourseProviderCostWhy It's Trusted
Red Teaming LLM ApplicationsDeepLearning.AI + GiskardFreeHands-on red teaming, prompt injection, jailbreak detection, bias testing.
AI AlignmentBlueDot ImpactFreeMost trusted free course on AI alignment and safety (formerly AI Safety Fundamentals). Used by professionals at Anthropic, DeepMind.
NeMo GuardrailsNVIDIAFreeHands-on notebooks for building production guardrails with NeMo Guardrails.

Coding Agents & Developer AI Tools

CourseProviderCostWhy It's Trusted
Claude Code: Official DocsAnthropicFreeThe definitive starting point for Claude Code. Covers CLAUDE.md (and reading an existing AGENTS.md), skills, hooks, subagents, the Agent SDK, and permissions.
Claude Code in ActionAnthropic (Claude Academy)FreeShort self-paced course (9 lessons, about an hour) on long, hands-off sessions: steering, configuration, automation, and verifying unsupervised runs.
Building Code Agents (Hugging Face)Hugging FaceFreeHuggingFace's official agents course, which includes a unit on building code-execution agents with smolagents.
OpenHands DocumentationOpenHandsFreeOfficial docs for the OpenHands autonomous coding agent: the browser canvas, the CLI, and the Software Agent SDK.

📖 Also see this repo's guides: Claude Code Guide and OpenCoder Landscape


For PMs & Non-Engineers

These require no Python experience:

CourseProviderCostWhy It's Good
AI for EveryoneDeepLearning.AI (Coursera)FreeAndrew Ng's course for non-technical roles. Covers what AI can/can't do, project leadership.
Prompt Engineering for EveryoneLearn PromptingFreePlain-English guide to prompt engineering for non-engineers.
AI Evals For Engineers & PMs (Maven)Hamel Husain & Shreya ShankarPaidDespite having code, this course is designed for PMs and QAs, not just engineers. Highly recommended.
AI Product Manager: Real Role or Buzzword?Product SchoolFree (blog)Practical guide to what an AI PM actually does, how it differs from a PM who uses AI tools, and the skills to build.
Google: Introduction to Generative AIGoogle Cloud Skills BoostFreeNo-code introduction to generative AI, LLMs, and responsible AI.

YouTube Channels & Free Content

Channel / ResourceFocusWhy Follow
Andrej KarpathyFoundations, transformersBest explanations of how LLMs actually work
Yannic KilcherPaper reviewsClear walkthroughs of latest ML research papers
Aleksa Gordić - The AI EpiphanyPaper reviewsDeep technical paper breakdowns
AI JasonAgents, LangChain, practicalGreat intro videos for agentic frameworks
Sam WitteveenGemini, RAG, agentsOne of the best practical AI YouTubers
Matt WolfeAI news, product demosBest for staying current on AI news and tools
Hamel Husain (blog)Evals, production AI, LLMsReal production insights from the author of the evals maven course
Simon Willison (blog)LLM news, tools, codingThe most trustworthy daily AI news source
The Latent Space podcastTechnical AI interviewsBest technical AI podcast, with deep dives with researchers
Lex Fridman PodcastBroad AI/ML interviewsLong-form interviews with leading AI researchers

Learning Path Suggestions

🛤️ Path: "I'm new to AI and want to build things fast"

text
Week 1: Prompt Engineering for Developers (DeepLearning.AI): free, 2 hrs
Week 2: Building Systems with ChatGPT API (DeepLearning.AI): free, 2 hrs
Week 3: Building and Evaluating Advanced RAG (DeepLearning.AI): free, 2 hrs
Week 4: AI Agents in LangGraph (DeepLearning.AI): free, 4 hrs
Month 2: Pick a real project, use this guide as reference

🛤️ Path: "I want to understand LLMs deeply"

text
Week 1-3: Neural Networks: Zero to Hero (Karpathy): free, 12+ hrs
Week 4-6: CS324 Stanford LLMs: free, 30+ hrs
Month 2: Generative AI with LLMs (Coursera DeepLearning.AI)
Month 3: CS294 LLM Agents (Berkeley)

🛤️ Path: "I want to build production-ready AI evaluation"

text
Week 1: Evaluating and Debugging Generative AI (DeepLearning.AI + W&B): free
Week 2: This repo's evals guides (Phoenix/Langfuse): free ← start here
Week 3-4: Quality and Safety for LLM Applications (DeepLearning.AI)
Month 2: AI Evals For Engineers & PMs (Maven, Hamel + Shreya): paid, worth it

🛤️ Path: "I'm a PM learning to contribute to AI product quality"

text
Week 1: AI for Everyone (Coursera): free
Week 2: Prompt Engineering for Everyone (learnprompting.org): free
Week 3: AI Evals guide in this repo: free (especially Chapters 1-3 on error analysis)
Month 2: AI Evals For Engineers & PMs (Maven): paid, has PM track

🛤️ Path: "I want to deploy coding agents in my team"

text
Day 1: Claude Code docs (code.claude.com): free
Week 1: This repo's Claude Code Guide + OpenCoder Landscape Guide
Week 2: Claude Code in Action (Claude Academy) + Building Code Agents (Hugging Face): free
Month 1: Run Claude Code on a real project in CI

How to Stay Current

AI moves fast. Beyond courses, these habits keep you current:

  1. Follow Simon Willison's blog: daily, trustworthy AI news summaries
  2. Read Anthropic + OpenAI release notes: primary sources beat second-hand summaries
  3. Watch the Latent Space podcast: best technical depth
  4. Contribute to open source (OpenHands, LlamaIndex, DSPy): real learning happens in PRs
  5. Star this repo: we update it as the landscape changes ⭐

Maintained by Om Bharatiya. PRs welcome for new course additions!

From the AI System Design Guide by Om Bharatiya · MIT License ·view source