Guides &
Playbooks
Curated guides, tutorials, and references across the AI engineering stack — from RAG pipelines and agent frameworks to vector databases, evals, and production architectures.
Building Your First RAG Pipeline
A step-by-step guide to building a production-ready Retrieval-Augmented Generation pipeline from scratch using LangChain, OpenAI embeddings, and Pinecone vector store.
Introduction to AI Agents
Understand what AI agents are, how they work, and how to build your first agent with tool-use, memory, and reasoning loops.
Getting Started with Smolagents (Hugging Face)
A practical introduction to Hugging Face's Smolagents framework — lightweight, modular agent building with code-driven actions and tool integration.
Choosing the Right Vector Database
Compare Pinecone, Weaviate, Qdrant, Chroma, and Milvus — performance, scalability, pricing, and use cases for each vector database.
LLM Fundamentals: How Large Language Models Work
A clear, non-technical explanation of how LLMs work — transformers, attention, tokenization, training, and inference.
Prompt Engineering: Patterns & Best Practices
Master prompt engineering with proven patterns — chain-of-thought, few-shot, structured outputs, system prompts, and persona-based prompting.
Running Local LLMs with Ollama
Set up and run LLMs locally using Ollama — from installation to running models like Llama 3, Mistral, and Phi-3 with a simple CLI.
Advanced RAG: Self-Querying & Agents
Go beyond basic RAG with self-querying retrievers, multi-hop reasoning, agentic RAG, and corrective retrieval strategies for production systems.
Building Multi-Agent Systems with CrewAI
Learn how to design and deploy multi-agent systems using CrewAI — assign roles, delegate tasks, and orchestrate agent collaboration.
Building Custom Tools for Smolagents
Create and share custom tools for Smolagents — from API wrappers to database connectors, and publish them on the Hugging Face Hub.
AI Evaluation Frameworks: A Complete Guide
Master AI evaluation with frameworks like LangSmith, MLflow, DeepEval, and custom eval pipelines. Measure accuracy, hallucination, and agent performance.
Building Custom Eval Pipelines for Agents
Design custom evaluation pipelines for AI agents — synthetic data generation, scenario testing, trajectory evaluation, and regression tracking.
Embedding Models: A Practical Guide
Compare OpenAI, Cohere, Sentence Transformers, and open-source embedding models. Learn about dimensionality, performance, and cost tradeoffs.
Understanding Model Context Protocol (MCP)
Learn how Model Context Protocol works — standardizing context windows, token budgeting, priority-based truncation, and multi-turn memory management.
n8n Automation: From Zero to Production
A complete guide to n8n workflow automation — from installing n8n to building complex multi-step automations with 400+ integrations.
Python for AI: Essential Libraries & Patterns
The essential Python libraries and patterns you need for AI development — from data processing to model deployment and API building.
Designing Scalable AI System Architectures
Architecture patterns for production AI systems — microservices for AI, async processing, caching strategies, model serving, and monitoring.
Best Open Source AI Tools for 2025
A curated list of the best open source AI tools for agent building, RAG, evaluation, monitoring, and deployment — all free and self-hostable.
Request a Guide
Is there a topic you want covered? Tell me what you're working on and I'll write a guide on it.
Suggest a Topic