— Práctica / IA
Ingeniería de IA, no demos de IA.
Cualquiera puede conectar un chatbot a un modelo. Nosotros hacemos la ingeniería de lo que viene después — recuperación, evaluaciones, salvaguardas, observabilidad y los sistemas que mantienen la función honesta en producción.
— Práctica / Qué entregamos
Lo que entregamos.
-
RAG en producción.
Vectorize sobre Cloudflare. Recuperación híbrida. Estrategias de segmentación ajustadas al corpus real, no a un tutorial.
-
Sistemas de agentes.
Anthropic SDK y OpenAI SDK con uso de herramientas, llamadas a funciones y la infraestructura poco vistosa que evita que un agente entre en bucle.
-
Servidores MCP.
Servidores Model Context Protocol sobre Cloudflare Workers — para Claude, Cursor o cualquier otro cliente MCP.
-
Evaluaciones como hábito.
Si no puedes medir las regresiones, no tienes un sistema de IA — tienes un prompt. Escribimos las evaluaciones dentro del pipeline de despliegue.
— Práctica / Qué no hacemos
Lo que no hacemos.
-
Entrenamiento o fine-tuning de modelos.
Si tu problema de verdad necesita pesos personalizados, te señalaremos a gente que se dedica a eso.
-
Chatbots pegados encima.
Un widget de chat en un sitio de marketing rara vez es la respuesta correcta. Diseñamos la IA como una función, no como un truco de interfaz.
-
«Genera el contenido y ya».
La generación de texto en volumen para marketing está bien cubierta por otras herramientas. Eso no es un encargo de ingeniería.
Stack — con criterio propio
Un juego de herramientas más pequeño, más profundidad.
Modelos
Anthropic Claude · OpenAI GPT · Cloudflare Workers AI
Recuperación
Cloudflare Vectorize · D1 · híbrido BM25
Orquestación
Anthropic SDK · OpenAI SDK · MCP · Workers
Observabilidad
Workers Logs · Sentry · evaluaciones a medida
Prompts
Versionados en el código · evaluados en CI
Superficie
API · agente · servidor MCP · interfaz integrada
Notas de campo — IA
Escritos recientes sobre la práctica.
-
What we learned running a public MCP server
We exposed our own site as a public, unauthenticated MCP server — six tools, stateless streamable HTTP, rate-limited where it costs money or sends email. The design decisions that mattered, and what we would do differently.
-
The US government now calls AI "Super Intelligence". What changes for your business
A September 2026 US executive order has federal agencies say "Super Intelligence" instead of AI. What it changes, what it does not, and what owners should do.
-
An AI receptionist for a small business: what it handles and where it fails
What an AI receptionist does well, where it breaks, and the guardrails to set before it answers your phone: approved answers, human handoff, and weekly review.
-
ChatGPT, Copilot, or Claude: choosing an AI assistant for a small team
How a small team can choose between ChatGPT, Microsoft Copilot, and Claude: where your work lives, what the work is, business plans, admin controls, and cost.
— Desde el GitHub
Plantillas que entregamos y mantenemos.
Patrones de producción funcionales que usamos nosotros mismos, con licencia MIT. Ambas se despliegan en tu propia cuenta de Cloudflare en menos de cinco minutos. Los artículos complementarios explican la arquitectura por completo.
-
Pipeline RAG de producción sobre Cloudflare Workers
-
Servidor MCP de producción sobre Cloudflare Workers
— Trabaja con nosotros
— Profundiza
Notas de campo sobre esta práctica
-
What we learned running a public MCP server
We exposed our own site as a public, unauthenticated MCP server — six tools, stateless streamable HTTP, rate-limited where it costs money or sends email. The design decisions that mattered, and what we would do differently.
-
AI meeting notes and transcription for small business: what is safe and what is not
AI notetakers can save real time, but they record, transcribe, and sometimes train on your conversations. A practical guide to the consent and data-handling risks, how to set them up safely, and when to leave the recorder off.
-
Before you turn on Microsoft 365 Copilot, fix your oversharing
Copilot only shows people what they can already access. That is exactly the problem in most tenants. Here is how to find overshared SharePoint and OneDrive content, clean up permissions and links, and run a sensible pilot before rolling Copilot out.
-
What it costs to run a retrieval-augmented AI system on Cloudflare
The honest cost anatomy of a RAG system on Cloudflare — embeddings, Vectorize, model inference, storage, and the request path — plus how the bill scales and where it surprises people. A method to estimate yours, not a fake total.
-
MCP Servers in Production: When to Build, When to Skip
Model Context Protocol is the best primitive Anthropic shipped in 2024 — and the most over-applied. A field guide to when an MCP server is the right answer, when it's overkill, and how to operate one in production on Cloudflare Workers.
-
Structured output from language models: getting reliable JSON instead of prose
Free-text model output breaks pipelines. Here is how schema-constrained generation, tool calling, validation, and retries turn a language model into a component you can build on — and where the approach still fails.
-
RAG evaluation: how to know your AI answers are actually correct
A retrieval system that sounds confident is not the same as one that is right. How to build an evaluation set, measure retrieval and faithfulness, run human spot-checks, and catch regressions before your users do.
-
When Not to Use an LLM
A working checklist for keeping large language models out of the places they don't belong: deterministic logic, unverifiable outputs, high-stakes decisions, and problems a database query already solves.
-
Making Your Website Agent-Ready: What Actually Matters in 2026
AI agents and answer engines read your site before people do. What makes a site legible to them — structured data, markdown, an AI-crawler policy, and MCP.
-
Workers AI vs OpenAI: A Cost-Quality Matrix at Low Volume
Most production AI features default to OpenAI by reflex. They shouldn't. A real comparison of Workers AI, OpenAI, and Anthropic Claude across the four tasks that actually show up in client engagements — embeddings, generation, transcription, classification — with real numbers and a routing strategy that uses each for what it's good at.
-
Production RAG on Cloudflare Without LangChain
A 200-line RAG pipeline on Cloudflare Workers + Vectorize + D1 — the five primitives that matter, why frameworks rot at the wrong layer, and how to keep retrieval debuggable in production.
¿Trabajas en algo con forma de IA? Cuéntanos.
Dos párrafos bastan. Respondemos por escrito, con una respuesta de encaja o no encaja, dentro de un día hábil.