Learning Resources and Courses

Official OpenAI guide for product and engineering teams building agentic applications, covering when to use agents, model and tool selection, orchestration patterns, guardrails, and evaluation.

Udacity nanodegree covering advanced prompting, agentic workflow patterns, tools, memory, and multi-agent systems through hands-on projects such as a travel planner and automated sales workflow.

DeepLearning.AI course by Andrew Ng covering agentic design patterns such as reflection, tool use, planning, and multi-agent collaboration, with Python implementations and a capstone research-agent project.

Free online book by Michael Brenndoerfer covering how AI agents work, including tool use, memory, multi-agent coordination, evaluation, observability, safety, and production operations.

Coursera course by Jules White focused on building agentic AI systems in Python, including tool discovery, function calling, agent-environment interaction, and practical autonomous workflows.

DeepLearning.AI short course taught by LangChain founder Harrison Chase on LangGraph components, agentic search, persistence, human-in-the-loop flows, and multi-step agent reasoning.

Chip Huyen's O'Reilly book on building applications with foundation models, covering prompt engineering, RAG, fine-tuning, agents, evaluation, deployment, and cost optimization for production AI systems.

Anthropic's research and engineering publication hub covering AI safety, interpretability, model evaluations, Claude system behavior, and practical guidance such as agent design patterns.

DeepLearning.AI short course taught by LlamaIndex CEO Jerry Liu on router agents, tool calling, multi-document agents, and agentic reasoning loops for research and document workflows.

Anthropic engineering guide that distinguishes workflows from agents and explains practical patterns such as prompt chaining, routing, parallelization, orchestrator-subagent workflows, and evaluator-optimizer loops.

Towards AI book by Louis-Francois Bouchard and Louie Peters covering production LLM application patterns, including prompting, retrieval-augmented generation, evaluation, fine-tuning, deployment, and operational pitfalls.

Technical blog by Chip Huyen covering AI engineering, production LLM applications, retrieval, evaluation, system design, and practical lessons for building machine learning systems.

Official Anthropic cookbook repository with notebooks and recipes for building with Claude, including RAG, classification, tool use, vision, prompt engineering, AWS examples, and practical API workflows.

Free Cohere curriculum covering language-model fundamentals, embeddings, semantic search, text generation, retrieval-augmented generation, and practical labs for building AI applications with Cohere APIs.

Andrej Karpathy lecture covering how large language models work, from tokenization and attention through training, RLHF, deployment behavior, and practical use patterns relevant to agent builders.

Free online version of the MIT Press deep learning textbook by Ian Goodfellow, Yoshua Bengio, and Aaron Courville, covering neural network foundations, optimization, architectures, and applications.

DeepLearning.AI course by CrewAI CEO Joao Moura covering CrewAI crews and flows, MCP integration, traces, LLM-as-a-judge evaluation, and production deployment for multi-agent systems.

Chip Huyen's O'Reilly book on production machine learning systems, covering data pipelines, model development, deployment, monitoring, infrastructure, and the human side of reliable ML systems.

Applied ML and AI engineering blog by Eugene Yan covering LLMs, recommendation systems, retrieval, evaluation, agents, and production lessons from real AI systems.

DeepLearning.AI short course on event-driven document agents with LlamaIndex workflows, RAG document processing, branching and looping logic, concurrent execution, and human-in-the-loop feedback.

Free code-first deep learning course by Jeremy Howard and Rachel Thomas covering neural networks, computer vision, NLP, model training, and practical development habits for AI builders.

Udacity course on adapting LLMs into agents with supervised fine-tuning, PEFT and LoRA, ReAct reasoning loops, trajectory data generation, Direct Preference Optimization, and alignment practices.

Practical course and resource hub for production deep learning, covering problem formulation, data work, model development, infrastructure, deployment, monitoring, and the lifecycle of AI-powered products.

Coursera course on building LangChain agents with tool calling, LCEL chaining, DataFrame and SQL agents, and structured AI workflows for Python developers.

Google Cloud training path covering generative AI, Gemini APIs, Vertex AI, agent development, and production AI application deployment on Google Cloud infrastructure.

Official Google Cloud certification for designing, building, and productionizing machine learning systems, including Vertex AI workflows, responsible AI, MLOps practices, and scalable model deployment on Google Cloud.

Official Google Cloud technical guide for building AI agents, covering architecture, tool use, evaluation, deployment, observability, and production practices across Google Cloud and Vertex AI.

ML engineering blog by Hamel Husain focused on LLM evaluation, fine-tuning, production AI systems, data-centric workflows, and practical engineering guidance for teams building with AI.

O'Reilly book by Jay Alammar and Maarten Grootendorst explaining LLM concepts and practical workflows such as tokenization, embeddings, fine-tuning, text generation, semantic search, and multimodal models.

Free course covering AI agent fundamentals, tools, actions, observations, smolagents, LangGraph, LlamaIndex, agentic RAG, and final benchmark-based projects for certification.

Hugging Face research feed highlighting daily trending machine learning papers with community discussion, links to arXiv, GitHub code, and coverage of LLMs, agents, benchmarks, and open models.

Free Hugging Face course on Model Context Protocol concepts and implementation, including MCP clients, servers, tool integration, and how agents connect to external data and services.

Official Hugging Face cookbook with practical notebooks for agents, retrieval-augmented generation, fine-tuning, multimodal AI, text generation, and deployments using open-source models and Hugging Face tooling.

Blog by Jason Liu, creator of Instructor, covering structured outputs, retrieval-augmented generation, data extraction, evals, and practical LLM engineering patterns for production systems.

Official LangChain learning platform with self-paced courses on deep agents, LangSmith essentials, agent observability, evaluation, and skills for building reliable LangChain and LangGraph applications.

Official LlamaIndex documentation and tutorials for agents, RAG, workflows, data connectors, vector stores, LlamaCloud, and production document retrieval systems.

GitHub handbook comparing LLM agent frameworks, scaffolding agent skeletons, collecting evaluation tools, and organizing domain examples across healthcare, finance, education, and other agent use cases.

Lilian Weng's widely cited blog post explaining LLM-powered agent architecture through planning, memory, tool use, task decomposition, reflection, and agent system case studies.

Comprehensive paid course covering CrewAI, AutoGen, AutoGPT, and other agent frameworks. No programming knowledge required, suitable for beginners to advanced learners.

Covers developing and deploying AI agents on Microsoft Azure platform. Official Microsoft training for enterprise-grade agent development and deployment.

Microsoft entry-level AI certification covering AI workloads, machine learning concepts, computer vision, natural language processing, generative AI, Azure AI services, and responsible AI fundamentals.

MIT's introductory deep learning course with lecture videos and labs covering neural networks, sequence modeling, computer vision, reinforcement learning, and practical model-building foundations.

Free course covering role-playing agents, memory management, tools integration, guardrails, cooperation patterns, and hands-on projects.

Andrej Karpathy's free video course and companion notebooks for building neural networks from scratch in Python, including micrograd, makemore, GPT-style language modeling, and tokenization.

NVIDIA-Certified Associate credential for foundational generative AI and LLM skills, including machine learning basics, prompt engineering, Python libraries, LLM integration, deployment, and NVIDIA solution awareness.

Official OpenAI Cookbook tutorial for building, deploying, evaluating, and optimizing an AgentKit workflow using Agent Builder, ChatKit, Evals, and prompt optimization.

Official OpenAI cookbook with examples and guides for agents, tool calling, retrieval, embeddings, fine-tuning, evaluations, structured outputs, and production application patterns.

Sutton and Barto's second-edition reinforcement learning textbook, covering Markov decision processes, dynamic programming, Monte Carlo methods, temporal-difference learning, function approximation, and agent decision-making.

Free courses on building AI agents with Salesforce's Agentforce platform. Covers agentic AI fundamentals and practical applications for enterprise environments.

Focuses on ReAct (Reasoning + Acting) prompting techniques for building responsive AI agents. Includes hands-on coding exercises for practical learning.

Stanford seminar course with researchers presenting on transformer architectures, large language models, agent applications, multimodal systems, and frontier AI research.

Andriy Burkov's concise machine learning book for engineers, covering core ML concepts, algorithms, model evaluation, neural networks, and practical foundations for building AI applications.

Practitioner guide by Eugene Yan, Bryan Bischof, Charles Frye, Hamel Husain, Jason Liu, and Shreya Shankar covering prompting, RAG, fine-tuning, evaluation, monitoring, and product lessons for production LLM systems.