<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title><![CDATA[Siva Reddy — AI Engineer & Writer]]></title>
        <description><![CDATA[Exploring AI, machine learning, and the future of intelligent systems. Writing about what I build and learn.]]></description>
        <link>https://sivareddyai.com</link>
        <generator>RSS for Node</generator>
        <lastBuildDate>Wed, 10 Jun 2026 07:11:23 GMT</lastBuildDate>
        <atom:link href="https://sivareddyai.com/rss.xml" rel="self" type="application/rss+xml"/>
        <pubDate>Wed, 10 Jun 2026 07:11:23 GMT</pubDate>
        <language><![CDATA[en]]></language>
        <item>
            <title><![CDATA[Why LLM Agents Fail in Production (And What to Do About It)]]></title>
            <description><![CDATA[Agents look impressive in demos but break in unpredictable ways in production. Here's what I've learned about the failure modes and how to design around them.]]></description>
            <link>https://sivareddyai.com/blog/why-llm-agents-fail</link>
            <guid isPermaLink="true">https://sivareddyai.com/blog/why-llm-agents-fail</guid>
            <category><![CDATA[Agents]]></category>
            <category><![CDATA[LLMs]]></category>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Fri, 15 May 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Token Cost Optimization Series, Part 1: Stop Sending JSON to Your LLM]]></title>
            <description><![CDATA[JSON repeats field names with every record, burning tokens at scale. Here's a simple format swap that cuts context token usage by 40–58% for tabular data.]]></description>
            <link>https://sivareddyai.com/blog/token-cost-optimization-stop-sending-json</link>
            <guid isPermaLink="true">https://sivareddyai.com/blog/token-cost-optimization-stop-sending-json</guid>
            <category><![CDATA[LLMs]]></category>
            <category><![CDATA[Cost Optimization]]></category>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Thu, 07 May 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[RAG Beyond the Basics: What Nobody Tells You]]></title>
            <description><![CDATA[Everyone can build a basic RAG pipeline. Making it production-ready is a different skill entirely. Here are the lessons I've learned the hard way.]]></description>
            <link>https://sivareddyai.com/blog/rag-beyond-basics</link>
            <guid isPermaLink="true">https://sivareddyai.com/blog/rag-beyond-basics</guid>
            <category><![CDATA[RAG]]></category>
            <category><![CDATA[LLMs]]></category>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Tue, 28 Apr 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How to Actually Evaluate LLM Outputs]]></title>
            <description><![CDATA[Vibes-based evaluation doesn't scale. Here's a practical framework for measuring LLM quality in ways that are reproducible, actionable, and honest.]]></description>
            <link>https://sivareddyai.com/blog/evaluating-llms</link>
            <guid isPermaLink="true">https://sivareddyai.com/blog/evaluating-llms</guid>
            <category><![CDATA[Evals]]></category>
            <category><![CDATA[LLMs]]></category>
            <category><![CDATA[Research]]></category>
            <pubDate>Tue, 10 Mar 2026 00:00:00 GMT</pubDate>
        </item>
    </channel>
</rss>