AI:Learning

A curated library of the best AI learning resources—courses, tutorials, docs, and talks on agentic AI, MCP, Agent Skills, RAG, machine learning, fine-tuning, models, and frameworks, for AI engineers and technical teams.

MLCourse

Modern LLM Notebook

WalkingLabs

A free notebook course that builds an LLM stack by hand, from BPE and GPT to MoE, DPO, speculative decoding and vLLM serving.

IntermediateFreeHands-onSelf-paced, 31 notebooks plus appendices; several weeks part-time (no official estimate)Nov 16, 2026
ModelsTutorial

Understanding Positional Embeddings in Modern LLMs

Sebastian Raschka (Ahead of AI)

How LLMs encode token position, from GPT-2's learned table to RoPE, partial RoPE and NoPE layers, with PyTorch code.

IntermediateFreeHands-on~40 min read, plus time to run the PyTorch snippetsNov 16, 2026
ModelsGuide

Building strong safety evaluations

Anthropic

Anthropic's method for designing, grading and reporting LLM safety evals, with sample-size floors and grader checks you can copy.

IntermediateFree~20 min read, longer if you follow the linked papersNov 16, 2026
AgenticGuide

Automating eval design and hillclimbing with Claude

Anthropic

How to design an eval you can trust and improve against it without overfitting, using claude-api build-eval and hillclimb.

IntermediateFreeHands-on~12 min read, plus hands-on time running the commands in Claude CodeNov 15, 2026
AgenticGuide

Building agents: When to fold subagents into your main agent loop

Anthropic

When one agent loop with skills and tool search beats a router plus specialist subagents, and how to migrate in stages.

IntermediateFreeHands-on~18 min read, plus a few hours with the companion migration kitNov 15, 2026
AgenticGuide

Building always-on agents

Anthropic

The five primitives behind a stateful, proactive agent: event inbox, timers, memory, permissions and outbox.

IntermediateFree~14 min readNov 15, 2026
Popular

Most Read This Week

The resources learners opened most this week.

  1. 1Claude Code 101Agentic · Course
  2. 2Deep Dive into LLMs like ChatGPTModels · Video
  3. 3CS146S: The Modern Software DeveloperAgentic · Course
  4. 4Evaluating AI AgentsAgentic · Course
  5. 5Building Effective AgentsAgentic · Guide
  6. 6Kaggle LearnML · Interactive
Fine-TuningDocumentation

prime-rl Documentation: Asynchronous Agentic RL Training at Scale

Prime Intellect

The open framework Prime Intellect used to post-train INTELLECT-3, with docs on async RL, loss design and scaling to large GPU clusters.

AdvancedFreeHands-on~4-6 hours to read the docs and run the 1-2 GPU smoke tests; multi-node runs take days of setupNov 14, 2026
FrameworksDocumentation

LangExtract: Python Library for Grounded Structured Extraction with LLMs

Google (open-source project)

Pull structured entities out of long documents with an LLM and trace every one back to its exact character offsets.

IntermediateFreeHands-on~1-2 hours to work through the README, examples and visualization, self-pacedNov 14, 2026
AgenticDocumentation

mini-swe-agent Documentation and Minimal AI Agent Tutorial

SWE-agent team (Princeton and Stanford)

Read a 100-line coding agent that scores above 74% on SWE-bench Verified, then build your own in about 60 lines of Python.

IntermediateFreeHands-on~1-2 hours for the from-scratch tutorial and quick start, self-paced; longer if you set up batch SWE-bench runsNov 14, 2026
AgenticCourse

Building and Deploying Managed Agents (LangChain Academy)

LangChain

LangChain's free course on taking a deep agent to production on LangSmith's managed runtime, with sandboxes, connections, schedules, auth, channels and evals.

IntermediateFreeHands-on24 lessons across 4 modules, including 3 hands-on labs, self-paced (the page lists no video hours)Nov 13, 2026
FrameworksCourse

LangChain.js for Beginners

Microsoft

A free Microsoft course that takes JavaScript and TypeScript developers from a first LLM call to agentic RAG and MCP servers with LangChain.js.

BeginnerFreeHands-on8 chapters plus a setup chapter, 70+ runnable examples, self-paced (no official hour estimate)Nov 13, 2026
AgenticBook

AI Agents and Applications: With LangChain, LangGraph, and MCP

Manning (Roberto Infante)

A project-driven Python book that goes from your first programmatic prompt to tool-using LangGraph agents, advanced RAG and your own MCP servers.

IntermediatePaidHands-on448-page book, 14 chapters plus 5 appendixes, self-paced with chapter-by-chapter Python codeNov 13, 2026
AgenticCourse

Design, Develop, and Deploy Multi-Agent Systems with CrewAI

DeepLearning.AI and CrewAI

A four-module CrewAI course that takes one code-review agent from prototype to a monitored, CI/CD-deployed multi-agent system.

BeginnerPaidHands-onCertificate~13 hours of video; Coursera estimates ~2 weeks at 10 hours/week including labsNov 12, 2026
ModelsCourse

Tabular Foundation Models for Data Science Agents

DeepLearning.AI and Prior Labs

Use TabPFN to predict on spreadsheets without training a model, then hand it to an LLM agent as a tool.

IntermediateFreemiumHands-on~1.5 hours of video and labs, self-pacedNov 12, 2026
Fine-TuningDocumentation

NeMo Data Designer Documentation: Synthetic Data Generation for LLM Training

NVIDIA

Generate validated synthetic training and evaluation data from samplers, LLMs, seed datasets, and agent traces.

IntermediateFreeHands-onSelf-paced: seven tutorial notebooks runnable in Google Colab; NVIDIA publishes no time estimateNov 11, 2026
AgenticDocumentation

NeMo Gym Documentation: Environments for Evaluating and Training LLM Agents

NVIDIA

Build agent environments and verifiers, run repeatable benchmarks, and feed the same setup into RL training.

AdvancedFreeHands-onSelf-paced reference docs; training tutorials are listed at 30 minutes (Unsloth), 1 hour (VeRL), and 3-5 hours (NeMo RL)Nov 11, 2026
ModelsCourse

Scalable AI: Bridging Theory, Understanding, and Practice (UC Berkeley EE 290 / 194, Fall 2026)

UC Berkeley

Follow a large language model from GPU performance limits through pre-training, post-training, and production inference.

AdvancedFreeHands-onOne semester (Aug 26 to Dec 18, 2026): 28 class sessions, about 42 hours of class time, plus four assignments of about 3-4 weeks eachNov 11, 2026
MLCourse

Large Language Models and Generative AI for NLP (University of Helsinki, Autumn 2026)

University of Helsinki (Aarne Talman, Jussi Karlgren, Dmitry Kan)

A seven-week master's course with public slides and labs that takes you from a tiny GPT to a tool-using agent.

IntermediateFreeHands-on7 weeks, 27 October to 10 December 2026; one 90-minute lecture and one 90-minute lab per week, plus a final projectNov 10, 2026
ModelsCourse

tiny-llm: LLM Inference Serving on Apple Silicon for Systems Engineers

Chi (skyzh) and Connor

Build Qwen3 inference, a mini vLLM and a coding agent from raw MLX array operations on a Mac.

AdvancedFreeHands-on4 weekly modules of 5 to 9 day-sized chapters, self-paced; the authors give no hour estimateNov 10, 2026
FrameworksCourse

Pydantic for LLM Workflows

DeepLearning.AI

Validate LLM output, user input and tool arguments with Pydantic models in a customer support assistant.

IntermediateFreemiumHands-onCertificate1h 50m listed, self-pacedNov 9, 2026
AgenticCourse

Agentic Knowledge Graph Construction

DeepLearning.AI and Neo4j

Use Google's ADK to build agents that turn CSV files and product reviews into one Neo4j knowledge graph.

IntermediateFreemiumHands-onCertificate3h 8m listed, self-paced (the individual lesson times add up to about 3h 15m)Nov 9, 2026
RAGCourse

Production Agentic RAG Course: arXiv Paper Curator

Jam with AI (Shirin Khosravi Jam and Shantanu Ladhwe)

Build an arXiv research assistant in seven stages, from Docker services and BM25 to hybrid search, tracing and a LangGraph agent.

IntermediateFreeHands-onWeek 0 overview plus 7 build weeks, self-paced; the authors publish no hour estimateNov 9, 2026
AgenticDocumentation

Kiro Documentation: Specs, Steering, Hooks and Agents for Spec-Driven Development

Kiro (AWS)

The official reference for Kiro's spec-driven agent workflow: requirements, design and task files, steering, hooks, MCP and custom agents across IDE, CLI and web.

IntermediateFreemiumHands-onSelf-paced reference; the docs put setup at under 5 minutes, and Get Started plus the Specs, Steering and Hooks pages take an afternoon to read and tryNov 8, 2026
AgenticCourse

Claude with Amazon Bedrock

Anthropic

Anthropic's free developer course for building Claude apps on Amazon Bedrock with boto3, from prompt evals and tool use to RAG, MCP and agents.

IntermediateFreeHands-onCertificateAbout 83 lesson items in 10 sections, self-paced; Anthropic gives no official length and a third-party guide says developer courses run longer than the 1-3 hour norm depending on exercisesNov 8, 2026