<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>SubstrAI Blog</title><description>Technical articles on serverless GenAI, AWS Lambda optimization, and building production AI systems.</description><link>https://substrai.dev/</link><language>en</language><item><title>From Use Case to Evaluation Pipeline in 10 Minutes</title><link>https://substrai.dev/blog/building-evaluation-pipelines/</link><guid isPermaLink="true">https://substrai.dev/blog/building-evaluation-pipelines/</guid><description>Every LLM deployment needs evaluation. Here&apos;s how to auto-generate complete evaluation infrastructure from a simple use case description.</description><pubDate>Mon, 10 Mar 2025 00:00:00 GMT</pubDate></item><item><title>Cost-Aware GenAI: Model Routing for Serverless</title><link>https://substrai.dev/blog/serverless-genai-cost-optimization/</link><guid isPermaLink="true">https://substrai.dev/blog/serverless-genai-cost-optimization/</guid><description>How to reduce GenAI costs by 60-80% using intelligent model routing that matches request complexity to the cheapest capable model.</description><pubDate>Sat, 15 Feb 2025 00:00:00 GMT</pubDate></item><item><title>Why LangChain Fails in Lambda (And What Does)</title><link>https://substrai.dev/blog/why-langchain-fails-in-lambda/</link><guid isPermaLink="true">https://substrai.dev/blog/why-langchain-fails-in-lambda/</guid><description>Existing LLM frameworks assume long-running servers with persistent memory. Here&apos;s why that breaks in AWS Lambda and how to solve it.</description><pubDate>Mon, 20 Jan 2025 00:00:00 GMT</pubDate></item></channel></rss>