Essays on building production software with AI agents: LLM evals, GEO, agentic development, and observability.https://pabloalbaladejo.comhttps://pabloalbaladejo.com/blog/geo-how-ai-agents-find-youhttps://pabloalbaladejo.com/blog/geo-how-ai-agents-find-youGenerative engine optimization (GEO) is how AI answer engines like ChatGPT and Perplexity cite you. A same-day case study of the five mechanisms I shipped on kaiord.com — from llms.txt to registries.Sat, 18 Jul 2026 00:00:00 GMThttps://pabloalbaladejo.com/blog/observability-for-llm-pipelineshttps://pabloalbaladejo.com/blog/observability-for-llm-pipelinesA practical guide to LLM observability: how to monitor LLM pipelines in production when classic APM misses streaming and agents — telemetry as a swappable sink, deferred-flush metrics, and real code.Sat, 11 Jul 2026 00:00:00 GMThttps://pabloalbaladejo.com/blog/evaluating-llm-outputs-in-productionhttps://pabloalbaladejo.com/blog/evaluating-llm-outputs-in-productionHow I evaluate LLM outputs in production: a 22-benchmark eval harness with tiered assertions and a hard 90% CI gate that fails the build on regressions.Sat, 04 Jul 2026 00:00:00 GMThttps://pabloalbaladejo.com/blog/shipping-production-software-with-ai-agentshttps://pabloalbaladejo.com/blog/shipping-production-software-with-ai-agentsCan AI agents write production code? Yes, if the system around them enforces quality mechanically. The agentic development workflow that ships production software.Sat, 27 Jun 2026 00:00:00 GMT