AI Engineering

Introductory map of AI Engineering: LLM products, RAG, agentic flows, guardrails, evaluation, cost, and the runtime around the model.

A broad historical and engineering panorama of AI: from ancient computing ideas and the perceptron to AlexNet, deep learning, and foundation models, with a focus on how algorithms, infrastructure, and product practice evolved together.

An introductory guide to core AI algorithms: search, evolutionary methods, swarm intelligence, ML, neural networks, and Q-learning. Best read as algorithmic groundwork before newer material on LLMs and generative systems.

A concise and practical introduction to deep learning and data analysis: fundamentals, classical machine learning algorithms, applied tasks, and hands-on work with TensorFlow, Keras, and PyTorch.

Chip Huyen on building AI applications around foundation models: prompting, RAG, agents, finetuning, evaluation, and operations.

Jay Alammar and Maarten Grootendorst: a visual practical guide to LLMs with ~300 illustrations covering tokenization, embeddings, transformers, RAG, and fine-tuning.

John Berryman and Albert Ziegler on designing prompts for LLMs, assembling context, using RAG and agent patterns, and evaluating answer quality.

How to design agentic systems: tool registries, planning and execution loops, state, approvals, and safe failure handling.

Jay Alammar and Maarten Grootendorst: a practical visual guide to agent systems covering memory, tools, planning, self-checking, multi-agent coordination, and engineering risks.

Original chapter about production RAG architecture: ingestion, retrieval, answer orchestration, guardrails, evaluation, and SLO-versus-cost trade-offs.

A practical chapter on designing LLM guardrails: prompt injection, tool abuse, output validation, policy checks, and safe degradation.

How to measure AI systems in production: offline evaluation, online metrics, historical replays, model-based scoring, human review, and observability loops.

Practical GenAI case: a multi-tenant enterprise assistant with ACL-aware retrieval, citations, evaluation, fallback chains, and cost guardrails.

Practical AI case: a coding-agent platform with workspace isolation, tool execution, approvals, observability, and safe SDLC automation.

A concise 2023 hands-on guide to the first generation of LLM applications: OpenAI API basics, prompting, prompt-injection mitigation, fine-tuning, and early LangChain patterns.

An Early Release O'Reilly guide to AI and GenAI interviews: 300 questions, strong answer patterns, common mistakes, and the signals interviewers expect.

Analysis of Lovable's history, business model, and conceptual architecture: from an open-source CLI to a cloud product with an agent-driven workflow.

Analysis of Dyad's architecture: multi-process Electron, a local execution stack, agent-and-tool orchestration, project templates, and checkpoints for safe rollback.

Extended talk about how engineering teams move from AI assistants to agent workflows in the SDLC: tools, protocols, governance, impact measurement, and practical adoption cases.

A talk by Yandex CTO Alexey Gusakov on how AI products move from hand-coded algorithms to designing intent, constraints, evaluation loops, and useful system behavior.

The official PyTorch documentary about how a research framework turned into one of the defining standards of modern AI engineering.

Documentary about AlphaGo's match against Lee Sedol and the engineering system that made the breakthrough possible.

Documentary about DeepMind's long research trajectory, from AlphaGo to AlphaFold and the next bets on the road to AGI.