“EU AI Act 2026: a technical checklist for Spanish CTOs”
"On 2 August 2026 high-risk, transparency and Commission enforcement powers kick in. A per-system checklist with downloadable template."
Category
Inteligencia Artificial
Artificial intelligence without the hype: models, agents, and use cases that work in production.
Agent observability with OpenTelemetry GenAI semconv in 2026
The OTel GenAI spec stabilizes attributes for LLMs, tools, and agents. Practical Python implementation with Anthropic + Grafana Tempo.
How to install and tune oMLX on M5 Max 128 GB
Tested May 2026 recipe: oMLX 0.3.8 on Mac M5 Max with 128 GB, TurboQuant at 3.5-bit, Qwen 3.6 35B-A3B model stack, Claude Code wiring and real benchmarks.
Multi-agent systems: LangGraph vs CrewAI vs Autogen in 2026
Three frameworks, three mental models. When to use each and why — with a real orchestration case.
How to build a production-ready agent with the Anthropic SDK, step by step
Full tutorial: tool use, streaming, prompt caching, observability, and your own MCP server. Reference repo included.
Claude Code vs Cursor vs GitHub Copilot in 2026: a comparison with measured tasks
Three production coding agents, five real tasks measured by time, tokens, and PR quality. No marketing — the actual measurement.
MCP (Model Context Protocol) in 2026: the complete guide for engineering teams
After eighteen months of multi-vendor adoption, MCP is the de facto standard for connecting models to tools. The complete guide: architecture, servers, policies, authentication, composition, and the antipatterns we've already seen in production.
Claude Opus 4.7 and long-horizon tasks: real changes
Opus 4.7 se lanzó como el modelo más capaz de Anthropic con énfasis en trabajo agéntico de horizonte largo. Tras dos meses de uso intensivo, estos son los cambios prácticos frente a Opus 4.6.
Hybrid RAG in 2026: the patterns that keep winning
Tres años después del boom inicial, el RAG en producción ha convergido en patrones híbridos que combinan búsqueda densa, léxica y reranking. Estos son los que sobreviven al paso del tiempo.
Claude Sonnet 4.6 in production: the cost-quality balance
Sonnet 4.6 es el modelo por defecto de la mayoría de cargas de trabajo en 2026. Estos son los casos donde brilla, dónde no basta y por qué sigue siendo el sweet spot.
Mature LLM-as-judge: when to trust and when not
Using an LLM to judge another LLM became widespread in 2024 and remains the only scalable way to evaluate qualitative quality. The mature question is when to trust those numbers.
MCP as multi-vendor standard: patterns already mature
The Model Context Protocol, proposed by Anthropic in late 2024 and adopted through 2025-2026 by every major vendor, has proven operational patterns. This is the state of the art.