--- title: Learning Paths, Courses & Books | The Agentic AI Hub — daily.dev description: Organized beginner → advanced. Pick a lane and go deep. Breadth comes with time. canonical: https://daily.dev/agentic-ai-hub/learning-paths-courses-books/ og:type: article og:url: https://daily.dev/agentic-ai-hub/learning-paths-courses-books/ og:title: Learning Paths, Courses & Books | The Agentic AI Hub — daily.dev og:description: Organized beginner → advanced. Pick a lane and go deep. Breadth comes with time. og:image: https://daily.dev/assets/og/agentic-ai-hub.png?v=40e6ff69 og:site_name: daily.dev og:locale: en_US article:modified_time: 2026-07-22 twitter:card: summary_large_image twitter:site: @dailydotdev twitter:creator: @dailydotdev twitter:title: Learning Paths, Courses & Books | The Agentic AI Hub — daily.dev twitter:description: Organized beginner → advanced. Pick a lane and go deep. Breadth comes with time. twitter:image: https://daily.dev/assets/og/agentic-ai-hub.png?v=40e6ff69 --- [Skip to main content ](#main-content) [   ](https://daily.dev/) [ Agentic AI Hub ](/agentic-ai-hub/) [   ](https://daily.dev/) / [ Agentic AI Hub ](/agentic-ai-hub/) [Get the app ](https://api.daily.dev/get?ref=docs-topbar) # Learning Paths, Courses & Books Too busy to read? Get an AI summary * Copy page Copy page Copy page as Markdown for LLMs [ View as Markdown View this page as plain text ](https://daily.dev/agentic-ai-hub/learning-paths-courses-books.md/) Table of Contents * [Roadmaps (start here to orient)](#roadmaps-start-here-to-orient) * [Beginner (build intuition + first models)](#beginner-build-intuition-first-models) * [Intermediate (build real things, understand internals)](#intermediate-build-real-things-understand-internals) * [Advanced (research depth + production scale)](#advanced-research-depth-production-scale) Organized beginner → advanced. Pick a lane and go deep. Breadth comes with time. ## Roadmaps (start here to orient) * **roadmap.sh (AI Engineer)**: [roadmap.sh/ai-engineer](https://roadmap.sh/ai-engineer). Visual, community-maintained path from fundamentals to building AI products. A good map of the territory. 🔄 * **roadmap.sh (AI/Data Scientist)**: [roadmap.sh/ai-data-scientist](https://roadmap.sh/ai-data-scientist). For the modeling and research side rather than the app side. * **roadmap.sh (AI Agents)**: [roadmap.sh/ai-agents](https://roadmap.sh/ai-agents). Design, build, and ship agents; the newest and most on-trend of the three roadmaps. 🔄 ## Beginner (build intuition + first models) * **Andrew Ng, Machine Learning Specialization**: [coursera.org/specializations/machine-learning-introduction](https://www.coursera.org/specializations/machine-learning-introduction). The classic on-ramp to ML fundamentals. * **DeepLearning.AI Short Courses**: [deeplearning.ai/short-courses](https://www.deeplearning.ai/short-courses/). Free 1-to-2-hour project courses on RAG, agents, and fine-tuning, built with the actual tool vendors. High ROI for practitioners. 🔄 * **3Blue1Brown, Neural Networks series**: [youtube.com/@3blue1brown](https://www.youtube.com/@3blue1brown). Watch before or alongside any course. The visual intuition sticks. * **Book: _AI Engineering_, Chip Huyen** (2025): [oreilly.com](https://www.oreilly.com/library/view/ai-engineering/9781098166298/). Intro to building applications on foundation models. A starting point for the app-builder path. * **Book: _Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow_, Aurélien Géron** (3rd ed., 2022): [oreilly.com](https://www.oreilly.com/library/view/hands-on-machine-learning/9781098125967/). The best-selling practical ML reference; code-first and thorough. ## Intermediate (build real things, understand internals) * **Andrej Karpathy, Neural Networks: Zero to Hero**: [karpathy.ai/zero-to-hero.html](https://karpathy.ai/zero-to-hero.html). Build a GPT from scratch, line by line. A free deep-learning course. * **fast.ai, Practical Deep Learning for Coders**: [course.fast.ai](https://course.fast.ai/). Top-down and code-first. Get models working, then learn why. * **Hugging Face Courses**: [huggingface.co/learn](https://huggingface.co/learn). Free NLP, LLM, agents, and RL courses using the HF stack; very hands-on. 🔄 * \*_Book: Build a Large Language Model (From Scratch), Sebastian Raschka_\* (2024): [manning.com](https://www.manning.com/books/build-a-large-language-model-from-scratch). Implement a full LLM yourself. The paper-to-code bridge. * **Book: _Hands-On Large Language Models_, Jay Alammar & Maarten Grootendorst** (2024): [oreilly.com](https://www.oreilly.com/library/view/hands-on-large-language/9781098150952/). Visual, practical guide to using and understanding LLMs. * **Book: _Natural Language Processing with Transformers_, Tunstall, von Werra & Wolf** (rev. ed., 2022): [oreilly.com](https://www.oreilly.com/library/view/natural-language-processing/9781098136789/). The canonical transformers/Hugging Face book, by HF's own authors. Pairs with the HF courses above. * **Course: _Generative AI with Large Language Models_ (DeepLearning.AI + AWS)**: [coursera.org/learn/generative-ai-with-llms](https://www.coursera.org/learn/generative-ai-with-llms). The de facto standard applied-LLM course: prompting, fine-tuning, and RLHF end to end. ## Advanced (research depth + production scale) * **Stanford CS224N (NLP with Deep Learning)**: [web.stanford.edu/class/cs224n](https://web.stanford.edu/class/cs224n/). Lectures on YouTube; the academic backbone for NLP and LLMs. * **Stanford CS336 (Language Modeling from Scratch)**: [stanford-cs336.github.io](https://stanford-cs336.github.io/). Build a full LLM training stack. About as close to how frontier labs work as a course gets. 🔄 * **Book: _Designing Machine Learning Systems_, Chip Huyen** (2022): [oreilly.com](https://www.oreilly.com/library/view/designing-machine-learning/9781098107956/). A production MLOps reference for shipping ML at scale. * **Book: _Deep Learning_, Goodfellow, Bengio, Courville** (2016): [deeplearningbook.org](https://www.deeplearningbook.org/). The foundational theory text, free online. Dense but canonical. * **Read the papers**: [Key Papers & Reading List](/agentic-ai-hub/key-papers-reading-list/) is itself the advanced curriculum. Reproduce one from scratch. Nothing teaches faster. > **A pragmatic path for a working developer (2026):** roadmap.sh/ai-engineer to orient → Karpathy Zero-to-Hero for internals → a couple of DeepLearning.AI short courses on RAG + agents → _AI Engineering_ (Huyen) → then ship something real and let [People to Follow (X/Twitter)](/agentic-ai-hub/people-to-follow/)/[Communities](/agentic-ai-hub/communities/) keep you current. The half-life of specific tools is short. The fundamentals and the _habit of following the frontier_ are what compound. Share this page Copy link [ Previous Events & Conferences ](/agentic-ai-hub/events-conferences/) [ Next AI Adoption Stats & Trends ](/agentic-ai-hub/ai-adoption-stats-trends/) [ Previous ](#) [ Next ](#) ### Table of Contents * [Roadmaps (start here to orient)](#roadmaps-start-here-to-orient) * [Beginner (build intuition + first models)](#beginner-build-intuition-first-models) * [Intermediate (build real things, understand internals)](#intermediate-build-real-things-understand-internals) * [Advanced (research depth + production scale)](#advanced-research-depth-production-scale) Link copied!