Category
Methodologies that respect your time: lightweight processes for small teams.
Using an LLM to judge another LLM became widespread in 2024 and remains, in 2026, the only scalable way to evaluate qualitative quality in LLM systems. It is reliable when judge-human correlation exceeds 0.7 on 30 cases and gets recalibrated quarterly; below that threshold, do not trust the number.
Opus 4.7 launched as Anthropic's most capable model, with emphasis on long-horizon agentic work. After two months of intensive use, these are the practical changes versus Opus 4.6.
The first invoice for a production agent usually runs double or triple the estimate. This article walks through five real levers, in priority order, caching, routing, context control, batching, and telemetry, to cut cost without touching perceived quality.
After fourteen months testing AI-integrated DevOps tools across several teams, the stack that stays is small: Claude Code, Cursor, and Aider for code; PagerDuty AIOps, Datadog Bits AI, and Grafana Assistant for alert triage; and OpenTofu with OPA for infrastructure generation bounded by policy rules.
AI agents fail in production, and what matters is how you respond in the first twenty minutes. This runbook covers severity classification, isolating before investigating, purging contaminated memory, communicating without inventing facts, and turning every incident into a regression test before closing it as done.
The RICE framework is a prioritization methodology created by Intercom that produces a score by combining four factors: Reach, Impact, Confidence, and Effort. It divides the product of the first three by the estimated effort in person-months, so it can compare unrelated initiatives using one objective number.
Prompt engineering has moved from viral tricks to a discipline with reproducible patterns: few-shot, chain-of-thought, and structured output with function calling. Teams treating prompts like code (versioned, tested, and monitored) get consistently better results than those who improvise.
Two years after the final NIST standards, post-quantum migration is no longer hypothetical. What has actually been migrated, what remains stuck, where the real operational problems lie, and how the timelines look from April 2026.
Tres años después de que platform engineering se convirtiera en palabra de moda, el polvo ha caído. Unas pocas empresas tienen plataformas internas que de verdad aceleran al desarrollo, muchas montaron un portal Backstage vacío y algunas volvieron a DevOps clásico. Análisis de qué distingue a las que ganaron.
La factura de IA en las empresas ha dejado de ser anecdótica. Entre tokens de modelos frontera, GPUs reservadas que nadie usa y pipelines RAG con cachés mal configuradas, muchos equipos pagan diez veces lo que deberían. Guía de FinOps específico para IA sin relatos promocionales.
Guardrails frameworks promise to filter language-model inputs and outputs to block data leaks, harmful content, or hallucinations. After evaluating four of the most popular ones in production, I cover what they actually do, what latency and billing cost they add, and when they pay off over simpler controls.
After three years of expansion and an overheated ecosystem around the term, platform engineering enters 2025 in a consolidation phase. The internal platforms that survive are the ones that understood their real function; those that mistook the label for the solution are dismantling their teams or cutting them drastically.
Probar sistemas que incluyen modelos de lenguaje rompe la primera regla del testing: la misma entrada da la misma salida. Analizo las estrategias que han funcionado tras un año largo integrando IA en productos reales, por qué los tests deterministas tradicionales no bastan y cómo plantear un cinturón de pruebas que capture regresiones sin bloquearse en la varianza.
Los equipos de producto están tentados de sustituir entrevistas y tests reales por síntesis de IA. Dos años de experiencia ya permiten separar dónde la IA ayuda de verdad y dónde genera una falsa sensación de entender al usuario.
Dependabot and Renovate chase the same goal with different philosophies. I compare both after years running them on my own and client projects, covering when one fits better and when the other suits a team's workflow more.
A year ago open weights were a gamble; today they are a real production option. I review what has worked, what has not, and how Llama, DeepSeek, Qwen, and Mistral are fitting into enterprise architectures that used to depend on closed APIs.
Two years into living with AI assistants in the editor, habits have settled. A reflection on what has changed in day-to-day coding, what has been learned, and what was still left to discover.
Three years after RLHF became popular, the model-alignment field is far richer. A review of RLHF, DPO, and newer methods such as KTO and ORPO, with criteria for choosing between them.
SLSA v1.0 splits software supply-chain security into three tracks (Build, Source, and Dependencies), of which only Build is stabilized, with three levels: L1, L2, and L3. If you build in GitHub Actions, reaching L2 with Sigstore-signed provenance takes a few hours and is the starting point I recommend to any team.
Measuring RAG quality rigorously takes more than skimming a handful of answers: it requires objective metrics (faithfulness, relevance, context precision, and coverage), a golden set of hundreds of curated questions, and regular human validation of the LLM judge to avoid misleading conclusions.
Software is not immaterial: every request and database query consumes electricity with a carbon footprint. The Green Software Foundation encodes eight practical principles to reduce that footprint without rewriting systems. The result is a more efficient service, a lower cloud bill, and readiness for ESG regulation.
Kubecost and OpenCost map real costs to namespaces, deployments, and labels in Kubernetes. OpenCost, the Apache 2.0 open-source core, covers essentials for free. Kubecost adds multi-cluster visibility and advanced cloud billing. For clusters spending over $5,000/month the ROI is clear: identified savings typically exceed software cost within the first month.
Chaos engineering is the practice of injecting real-world failures into production in a controlled way to verify that the system responds as expected. It requires prior hypotheses, a minimal blast radius, and mature observability. Open-source tools like Litmus and Chaos Mesh make adoption accessible without commercial spend; the ROI comes as avoided incidents and better-prepared teams.
Ansible and Pulumi solve different problems and are not competitors: Ansible manages configuration inside a server (packages, users, services); Pulumi defines, with real code in TypeScript, Python, Go or .NET, which cloud infrastructure exists (VPCs, instances, databases). Combining them, with Pulumi's dynamic inventory feeding Ansible, is the most productive pattern for automating a stack that includes servers in the cloud.
