Reflection in AI Agents: Self-Reflection and Cross-Reflection
How an AI agent evaluates and improves its own output using self-reflection and cross-reflection. Step-by-step code guide for developers getting started.
Library
All AI Coding Patterns
Technical articles: agents, architecture, tools and design decisions.
Tool use: how an LLM accesses external tools
LLMs can't see the current time or your database. Tool use gives them that access. I explain the loop, tool definition, and the most common mistakes.
Parallelization in AI Agents: Sectioning and Voting step by step
Learn how to run AI tasks in parallel: Sectioning divides the work, Voting repeats for higher reliability. Code guide for junior developers.
Routing in AI: How to Classify and Delegate Tasks Successfully
The Router pattern classifies user input and delegates it to the right agent. Learn how to implement it with rules, semantics, and fallback chains.
New
GoF Patterns in AI Agents: The Complete Map
GoF patterns don't disappear in agentic systems—they transform. Command=tool call, Mediator=orchestrator, Adapter=MCP. The complete map with code.
Prompt Chaining: How to Break Down Complex Tasks Into Simple Steps
Learn how to divide difficult tasks into sequential LLM calls. With line-by-line commented TypeScript code and no external frameworks.
OpenAI Privacy Filter: Detect PII Without Sending Data to the Cloud
Detect names, emails, and passwords in text without sending data to the cloud. Learn how it works and how to use it from Python.
Traditional Chatbot vs LLM: The Differences That Actually Matter
How a chatbot with intent classification works, how one based on an LLM works, and when to choose each approach with concrete examples.
Claude Code Auto Mode: Configure autoMode.environment
Set up autoMode.environment so the classifier understands your infrastructure and stops interrupting you with false positives.
LLMs Don't Understand Anything. And Yet They Work.
An LLM predicts the next most probable token. It doesn't understand. So how does it produce outputs that seem to require real comprehension?
Prompt Injection: How Hackers Hijack AI Agents
What is prompt injection, OWASP's #1 vulnerability for LLMs, how the attack works, and how to protect your app from day one.
AI Automation Without Code: 5 Real Workflows to Get Started
How to build AI automations using Zapier, Make, or n8n. Five real workflows, comparison table, and a framework for choosing your first automation.
Guardrails in AI Agents: What They Are and How to Implement Them
Guardrails prevent AI agents from deleting data, leaking information, or entering loops. Learn what they are and how to implement them with code from scratch.
Model as Judge: Evaluate Your AI Agent's Responses
Learn how to use an AI model to automatically evaluate another agent's responses. Rubrics, evaluation types, and the most common pitfalls.
Claude Projects: A Practical Guide to Get Started Today
Learn how to set up Projects in Claude from scratch: custom instructions, knowledge files, and real-world examples for different profiles.
The Language Tax: Why Different Languages Consume More Tokens
AI models break text into tokens. Spanish needs more than English to say the same thing. Here's why and what impact it has on your projects.
Temperature in LLMs: What It Is and What Value to Use for Your Case
What temperature is in language models, how it affects responses, and how to choose the right value for your task. Examples with the same prompt.
Context Window and Best Practices
What a language model's context window is, how it's measured in tokens, and concrete practices to leverage it from day one.
Architecture of an Enterprise Agent: The 6 Decisions That Matter
The 6 architectural decisions for your first production AI agent: precise objective, memory, tools with minimum privilege, and human oversight.
How to Make Your Agents Improve Themselves With This Skill
The methodology I use to make Claude Code improve itself through measuring, proposing hypotheses, iterating, and validating results
When to use skills in Claude Code: the complete map
Skills, hooks, CLAUDE.md: the complete map of Claude Code's 8 tools and when to use each one. A practical guide for beginners.
Introduction to Embeddings and Semantic Search
How to transform text into numerical vectors and build real semantic search. From cosine similarity to RAG, with diagrams, TypeScript code, and interactive exercises.
Prompt Engineering for Developers: The 5 Essential Patterns
The 5 prompt engineering patterns: zero-shot, few-shot, CoT, role prompting, and structured output with real TypeScript code.
What is MCP: the protocol connecting AI agents with tools
MCP (Model Context Protocol) standardizes how AI agents connect to external tools. Explanation with line-by-line commented Python examples.
Enterprise RAG: the complete pipeline that actually works
How to build a production RAG with semantic chunking, hybrid search and reranking. The real decisions that determine whether your system retrieves well or fails silently.
La IA programa rápido pero rompe cosas: estrategia de tests
La IA genera código en segundos pero no conoce tus dependencias. La estrategia de tests que funciona con agentes de programación.
How to evaluate AI agents in production: metrics, evals, and observability
Technical guide to measuring the real reliability of AI agents in production: task completion rate, deterministic evals, LLM-as-judge, and silent degradation detection.
TypeScript and AI Agents: Why the Language You Choose Matters
The language you use affects how your AI reasons. Three concrete mechanisms by which TypeScript improves code generated by agents like Claude Code.
40% of AI Agent Projects Will Be Canceled Before 2027. Here's Why
Gartner predicts over 40% of enterprise AI agent projects will be canceled before 2027. Tool loop, prompt injection, and MCP explained without the hype.
The Golden Age of the Programmer: Are You Taking Advantage of It?
Every time the cost of programming has fallen, the number of developers has grown. That's why I think we're in the best era to be a developer.
Claude Code Hooks: calidad determinista para garantizar proyectos mantenibles
Cómo usar Claude Code Hooks para añadir gates de calidad que el modelo no puede saltarse: lint, tests, OpenAPI y seguridad antes de cada commit.
Programmatic Tool Calling : Step-by-Step Implementation
Hay una técnica que permite ejecutar docenas de herramientas en paralelo sin que el modelo vea ningún resultado intermedio. Nadie habla de ella porque está enterrada en la especificación. Cuando la descubras, vas a replantear cómo diseñas cualquier pipeline de agentes.
AGENTS.md: The Configuration That Can Break Your Agent
Data shows poorly written AGENTS.md files reduce success rates by 2% and increase costs by 20%. Here's how to write yours correctly.