Learn agentic AI

Watch

• Intro to Large Language Models — Andrej KarpathyVideo
• Agentic AI: A Progression of Language Model Usage — StanfordLecture
• Building Effective AgentsVideo
• Building Agents with MCPVideo
• Building and Evaluating AgentsVideo
• Building an Agent from ScratchVideo
• Building Large Language Models — Stanford CS229Video
• Philo Agents — full playlistPlaylist
• Deep Dive into LLMs like ChatGPT — Andrej KarpathyVideo
• Let's build GPT: from scratch — Andrej KarpathyVideo
• Software Is Changing (Again) — Andrej KarpathyVideo
• Neural Networks: Zero to Hero — Andrej KarpathyPlaylist
• Neural networks — 3Blue1BrownPlaylist
• NIST — Intro to the AI Risk Management Framework (explainer)Security

Build

• Microsoft — AI Agents for BeginnersGitHub
• GenAI Agents — nirdiamantGitHub
• LLM Course — mlabonneGitHub
• Hands-On AI Engineering — Sumanth077GitHub
• Prompt Engineering GuideGitHub
• Hands-On Large Language ModelsGitHub
• Made With MLGitHub
• Awesome Generative AI GuideGitHub
• Designing Machine Learning SystemsGitHub
• Machine Learning for Beginners — MicrosoftGitHub
• Generative AI for Beginners — MicrosoftGitHub
• Claude Cookbooks (Anthropic)GitHub
• OpenAI CookbookGitHub
• Hugging Face TransformersGitHub
• LangChainGitHub
• OllamaGitHub
• Google Gemini CookbookGitHub
• MCP Servers — reference implementationsGitHub
• A2A — Agent2Agent ProtocolGitHub
• llama.cpp — local inferenceGitHub
• vLLM — high-throughput servingGitHub
• Langfuse — agent evals & observabilityGitHub
• OWASP Top 10 for LLM ApplicationsSecurity
• garak — LLM vulnerability scanner (NVIDIA)Security
• PyRIT — AI red-teaming toolkit (Microsoft)Security
• PurpleLlama — trust & safety tooling (Meta)Security
• Awesome ML Security — Trail of BitsSecurity
• Awesome LLM SecuritySecurity

Reference

• Building Effective Agents — AnthropicGuide
• Effective Context Engineering for AI Agents — AnthropicGuide
• OpenAI's Practical Guide to Building AgentsGuide
• Google's Agent WhitepaperGuide
• Google's Agent CompanionGuide
• Claude Code — Best Agentic Coding PracticesGuide
• Hugging Face — AI Agents Course (free)Course
• Anthropic — Prompt Engineering (docs)Docs
• Model Context Protocol — IntroductionDocs
• Model Context Protocol — SpecificationDocs
• A2A Protocol — documentationDocs
• OpenAI — Prompt Engineering (docs)Docs
• DeepLearning.AI — CoursesCourse
• OWASP GenAI Security ProjectSecurity
• OWASP Top 10 for LLM Applications (2025)Security
• OWASP Top 10 for Agentic Applications (2026)Security
• NIST — AI Risk Management FrameworkStandard
• NIST AI 600-1 — Generative AI ProfileStandard
• NIST — Cybersecurity Framework 2.0Standard
• MITRE ATLAS — adversarial ML threat matrixSecurity
• Google — Secure AI Framework (SAIF)Security
• EU AI Act — regulatory frameworkRegulation
• Microsoft — Responsible AIGovernance
• Cloud Security Alliance — AI Safety InitiativeSecurity
• HL7 FHIR R4 — specificationStandard
• ONC/ASTP — HTI rulesRegulation
• TEFCA — Trusted Exchange FrameworkRegulation

Read

• Building a Large Language Model (From Scratch)Book
• Understanding Deep Learning — freeBook
• LLM Engineer's Handbook — Iusztin & LabonneBook
• AI Agents: The Definitive Guide — Nicole KoenigsteinBook
• Building Applications with AI Agents — Michael AlbadaBook
• AI Agents with MCP — Kyle StratisBook
• Dive into Deep Learning — freeBook
• The Little Book of Deep Learning — Fleuret, freeBook
• Neural Networks and Deep Learning — Nielsen, freeBook
• Speech and Language Processing — Jurafsky & Martin, freeBook
• AI Engineering — Chip HuyenBook
• Hands-On Large Language Models — Alammar & GrootendorstBook
• Site Reliability Engineering — Google, freeBook
• The Developer's Playbook for LLM Security — Steve WilsonSecurity
• Adversarial AI: Attacks, Mitigations & Defense Strategies — John SotiropoulosSecurity