<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Fábio Silva — Ideas &amp; Guides</title><description>Developer building practical software where AI is a solution to real challenges, not the goal.</description><link>https://madebyfabio.dev/</link><language>en-gb</language><item><title>Stop chasing the benchmark, start shipping</title><link>https://madebyfabio.dev/ideas/stop-chasing-the-benchmark/</link><guid isPermaLink="true">https://madebyfabio.dev/ideas/stop-chasing-the-benchmark/</guid><description>Every week a new model tops a new leaderboard, and every week someone rewrites their stack to chase it. Why the &apos;best AI model&apos; debate is the wrong debate — and what actually separates teams that ship reliable AI from teams that don&apos;t.</description><pubDate>Sat, 27 Jun 2026 00:00:00 GMT</pubDate><category>ai</category><category>llm</category><category>strategy</category><category>development</category></item><item><title>Europe lights up faintly on the AI map — and that should worry us more than the China panic</title><link>https://madebyfabio.dev/ideas/europe-ai-compute/</link><guid isPermaLink="true">https://madebyfabio.dev/ideas/europe-ai-compute/</guid><description>What the global distribution of AI computing power means for Europe — as a union, and for the companies that run on it. An interactive map of who owns the world&apos;s compute, and an argument for optionality over autarky.</description><pubDate>Thu, 25 Jun 2026 00:00:00 GMT</pubDate><category>ai</category><category>infrastructure</category><category>europe</category><category>strategy</category></item><item><title>Agentic RAG: why your retrieval pipeline needs a brain</title><link>https://madebyfabio.dev/ideas/agentic-rag/</link><guid isPermaLink="true">https://madebyfabio.dev/ideas/agentic-rag/</guid><description>A retrieval pipeline that fetches but never reasons fails silently — a confidently wrong answer with no error thrown. Agentic RAG hands the LLM real agency over how grounding happens, and the engineering discipline that demands.</description><pubDate>Wed, 24 Jun 2026 00:00:00 GMT</pubDate><category>ai</category><category>rag</category><category>architecture</category><category>engineering</category></item><item><title>The complete n8n self-hosting guide</title><link>https://madebyfabio.dev/guides/self-hosting-n8n/</link><guid isPermaLink="true">https://madebyfabio.dev/guides/self-hosting-n8n/</guid><description>A practical, production-minded walkthrough for self-hosting n8n — from npx and a single Docker container to Docker Compose behind a reverse proxy and full Kubernetes deployments across AWS, Azure, GCP, and OpenShift. Faithful to the official docs, with sources linked throughout.</description><pubDate>Wed, 24 Jun 2026 00:00:00 GMT</pubDate><category>tutorial</category><category>self-hosting</category><category>docker</category><category>kubernetes</category><category>devops</category></item><item><title>Shipping AI in the enterprise: a builder&apos;s field guide</title><link>https://madebyfabio.dev/guides/shipping-ai-in-the-enterprise/</link><guid isPermaLink="true">https://madebyfabio.dev/guides/shipping-ai-in-the-enterprise/</guid><description>Most enterprise AI doesn&apos;t fail in the model — it fails in the last mile: integration, evals, rollout, people. A repeatable, phase-gated method for taking AI from idea to production, written from the project manager, AI engineer, and software developer seats at once.</description><pubDate>Wed, 24 Jun 2026 00:00:00 GMT</pubDate><category>ai</category><category>delivery</category><category>enterprise</category><category>architecture</category><category>product</category></item><item><title>AI as a solution, not the goal</title><link>https://madebyfabio.dev/ideas/ai-as-a-solution-not-the-goal/</link><guid isPermaLink="true">https://madebyfabio.dev/ideas/ai-as-a-solution-not-the-goal/</guid><description>Most failed AI projects didn&apos;t fail because the model was bad. They failed because nobody asked what challenge it was for. A case for challenge-first development.</description><pubDate>Sat, 11 Apr 2026 00:00:00 GMT</pubDate><category>opinion</category><category>ai</category><category>development</category></item><item><title>Structured outputs that don&apos;t break in production</title><link>https://madebyfabio.dev/guides/structured-outputs-that-dont-break/</link><guid isPermaLink="true">https://madebyfabio.dev/guides/structured-outputs-that-dont-break/</guid><description>A practical pattern for getting reliable, schema-valid JSON out of an LLM — with validation, retries, and a deterministic fallback — so a bad response never takes down your feature.</description><pubDate>Sun, 08 Feb 2026 00:00:00 GMT</pubDate><category>tutorial</category><category>ai</category><category>typescript</category><category>reliability</category></item></channel></rss>