<?xml version='1.0' encoding='utf-8'?>
<rss version="2.0"><channel><title>Reinaldo León — Writing</title><link>https://reinaldoleon.github.io/bio/writing/</link><description>Technical writing on AI Platform Engineering and reliable AI systems.</description><language>en</language><item><title>What's the difference between using AI to build software and running AI in production?</title><link>https://reinaldoleon.github.io/bio/en/writing/ai-assisted-engineering-vs-production-ai-runtime/</link><guid>https://reinaldoleon.github.io/bio/en/writing/ai-assisted-engineering-vs-production-ai-runtime/</guid><description>A practical architecture for separating AI-assisted engineering from production AI runtime controls while sharing platform capabilities.</description><pubDate>Mon, 16 Nov 2026 00:00:00 GMT</pubDate></item><item><title>Why doesn't every AI Engineering problem need another LLM?</title><link>https://reinaldoleon.github.io/bio/en/writing/ai-engineering-without-another-llm/</link><guid>https://reinaldoleon.github.io/bio/en/writing/ai-engineering-without-another-llm/</guid><description>When to use deterministic checks, when an LLM adds value, and how to connect reasoning with verifiable evidence in AI Engineering.</description><pubDate>Mon, 02 Nov 2026 00:00:00 GMT</pubDate></item><item><title>What happens when your AI agent can write code but cannot show how it got there?</title><link>https://reinaldoleon.github.io/bio/en/writing/ai-agent-code-traceability/</link><guid>https://reinaldoleon.github.io/bio/en/writing/ai-agent-code-traceability/</guid><description>Why code generation is not enough for governed software delivery, and what AI-DLC Workflows reveals about evidence, approvals and proportional control.</description><pubDate>Mon, 02 Nov 2026 00:00:00 GMT</pubDate></item><item><title>What does it take to make AI work beyond the demo?</title><link>https://reinaldoleon.github.io/bio/writing/from-model-capability-to-operating-capability/</link><guid>https://reinaldoleon.github.io/bio/writing/from-model-capability-to-operating-capability/</guid><description>A platform engineering view of the controls, evidence and ownership needed to operate AI beyond a promising demo.</description><pubDate>Thu, 29 Oct 2026 00:00:00 GMT</pubDate></item><item><title>Can AI help evaluate technical candidates without deciding for us?</title><link>https://reinaldoleon.github.io/bio/writing/ai-assisted-technical-interviews-without-outsourcing-judgment/</link><guid>https://reinaldoleon.github.io/bio/writing/ai-assisted-technical-interviews-without-outsourcing-judgment/</guid><description>What an AI-assisted technical exercise review can reveal, where bias can enter and why the hiring decision must remain human.</description><pubDate>Thu, 29 Oct 2026 00:00:00 GMT</pubDate></item><item><title>What happens when AI agent adoption grows faster than your governance?</title><link>https://reinaldoleon.github.io/bio/en/writing/ai-agent-adoption-governance/</link><guid>https://reinaldoleon.github.io/bio/en/writing/ai-agent-adoption-governance/</guid><description>A platform engineering view of the contracts, context and controls needed when AI agents spread across engineering teams.</description><pubDate>Thu, 29 Oct 2026 00:00:00 GMT</pubDate></item></channel></rss>