CrewAI

Free 84‑page AI handbook for LLMs and agents

Vinicius Pereira published a free 84-page handbook titled "Artificial Intelligence in Practice" that guides beginners from basic LLM concepts (tokens, context windows, temperature) through running models locally and building AI agents. The book, available on GitHub under a CC BY-NC-SA license, covers foundations, running models on personal hardware (mentions Ollama and Apple Silicon), Retrieval-Augmented Generation (embeddings, vector databases, chunking), multi-agent orchestration (CrewAI, LangGraph, tool integrations, browsing, MCP), and deeper topics like fine-tuning, cost, security, privacy, and testing. It includes three capstone projects and was hand-tested; prices and version numbers were verified in mid-2026. The author plans to serialize some chapters on dev.to.

Build a Resume-Tailoring AI Agent with CrewAI and Bedrock

A hands-on tutorial by Sarvar Nadaf that shows how to build a single-agent AI application which analyzes a job description (and an optional resume) to identify key skills, skill gaps, career guidance, and rewrite resume bullets. The guide uses CrewAI for orchestration, Amazon Bedrock (Nova Pro) for model inference, and a Streamlit web UI. It provides step-by-step commands, configuration (Python 3.11, uv package manager, CrewAI CLI), project scaffolding, sample inputs, and a GitHub repo with full source code. The app runs on a single EC2 instance (t3.medium) and stores results to a markdown file; the author outlines next steps toward a multi-agent architecture.

17‑Layer AI Engineer Roadmap to Production

This article presents a 17-layer roadmap for becoming an AI Engineer, covering skills from foundational Python and data handling through software engineering, prompt engineering, LLM fundamentals, embeddings, vector databases, RAG pipelines, orchestration, agentic workflows, state/memory management, and production deployment and monitoring. It recommends specific tools and libraries (e.g., Pandas, NumPy, LangChain, LlamaIndex, Pinecone, Chroma, Qdrant, Milvus, FastAPI) and operational practices (OpenTelemetry, tracing, streaming, containerization). The guide warns against skipping foundational steps before building multi-agent or agentic systems, and includes brief mentions of external industry items: a Chinese Z.AI firm announcing GLM-5.2 with a 1M-token context window and an Anthropic CFO claim about Claude writing over 90% of the company’s code and annualized revenue surpassing $30 billion.