<?xml version='1.0' encoding='utf-8'?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Antonio V. Franco</title><link>https://antoniovfranco.com/blog/en/</link><description>AI Engineering &amp; Efficient Models</description><language>en</language><atom:link href="https://antoniovfranco.com/blog/en/index.xml" rel="self" type="application/rss+xml" /><item><title>What does it cost to replace SaaS tools with OpenClaw and open-source software?</title><link>https://antoniovfranco.com/articles/openclaw-open-source-saas-replacement-costs/en/</link><guid>https://antoniovfranco.com/articles/openclaw-open-source-saas-replacement-costs/en/</guid><description>Compare SaaS subscriptions with OpenClaw, hosting, AI and maintenance costs, including a savings simulation and investment payback.</description><pubDate>Mon, 02 Nov 2026 09:00:00 -0300</pubDate></item><item><title>SLM fine-tuning: why marketplaces are rethinking the cost of enriching their catalogs</title><link>https://antoniovfranco.com/articles/slm-fine-tuning-marketplace-catalog-enrichment-costs/en/</link><guid>https://antoniovfranco.com/articles/slm-fine-tuning-marketplace-catalog-enrichment-costs/en/</guid><description>What Amazon's studies reveal about adapting small models to reduce the cost of extracting product attributes.</description><pubDate>Sat, 31 Oct 2026 09:00:00 -0300</pubDate></item><item><title>Why n8n 3.0 still does not replace LangGraph for AI agent engineering</title><link>https://antoniovfranco.com/articles/why-n8n-3-0-still-does-not-replace-langgraph/en/</link><guid>https://antoniovfranco.com/articles/why-n8n-3-0-still-does-not-replace-langgraph/en/</guid><description>What changes in n8n 3.0, and why I still choose LangGraph when agents need state control and recovery after failures.</description><pubDate>Thu, 29 Oct 2026 09:00:00 -0300</pubDate></item><item><title>Can a smaller agent do the work of a larger model? The new economics of agentic fine-tuning</title><link>https://antoniovfranco.com/articles/smaller-agent-larger-model-agentic-fine-tuning/en/</link><guid>https://antoniovfranco.com/articles/smaller-agent-larger-model-agentic-fine-tuning/en/</guid><description>When can a smaller agent complete a business task more economically than a larger general-purpose model?</description></item></channel></rss>