<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Mahesh Babu Gorantla - Tech Blog</title><link>https://maheshbabugorantla.github.io/</link><description>Recent content on Mahesh Babu Gorantla - Tech Blog</description><generator>Hugo -- 0.160.0</generator><language>en-us</language><lastBuildDate>Wed, 18 Mar 2026 12:00:00 -0600</lastBuildDate><atom:link href="https://maheshbabugorantla.github.io/index.xml" rel="self" type="application/rss+xml"/><item><title>Monitoring LLM Usage with OpenSearch &amp; OpenLLMetry</title><link>https://maheshbabugorantla.github.io/posts/monitoring-llm-usage-opensearch-openllmetry/</link><pubDate>Wed, 18 Mar 2026 12:00:00 -0600</pubDate><guid>https://maheshbabugorantla.github.io/posts/monitoring-llm-usage-opensearch-openllmetry/</guid><description>A hands-on guide to monitoring LLM cost, latency, and errors with OpenSearch and OpenLLMetry. From zero-code instrumentation to a full 9-panel cost dashboard — including the field-mapping gotchas that cost me a full debugging session.</description></item><item><title>From Span Hacks to Ingest Pipelines: Server-Side LLM Cost Enrichment with Elastic APM</title><link>https://maheshbabugorantla.github.io/posts/server-side-llm-cost-enrichment-elastic-apm/</link><pubDate>Sun, 22 Feb 2026 12:00:00 -0600</pubDate><guid>https://maheshbabugorantla.github.io/posts/server-side-llm-cost-enrichment-elastic-apm/</guid><description>Replace the CostEnrichingSpanExporter with an Elasticsearch enrich pipeline: centralized pricing, retroactive corrections, zero SDK coupling.</description></item><item><title>Monitoring LLM Usage with Elastic APM &amp; OpenLLMetry</title><link>https://maheshbabugorantla.github.io/posts/monitoring-llm-usage-elastic-apm-openllmetry/</link><pubDate>Sun, 15 Feb 2026 12:00:00 -0600</pubDate><guid>https://maheshbabugorantla.github.io/posts/monitoring-llm-usage-elastic-apm-openllmetry/</guid><description>A hands-on guide to monitoring LLM cost, latency, and errors with Elastic APM and OpenLLMetry. From zero-code instrumentation to full observability.</description></item><item><title>About</title><link>https://maheshbabugorantla.github.io/about/</link><pubDate>Sun, 15 Feb 2026 10:00:00 -0600</pubDate><guid>https://maheshbabugorantla.github.io/about/</guid><description>&lt;h2 id="about-me"&gt;About Me&lt;/h2&gt;
&lt;p&gt;I&amp;rsquo;m Mahesh Babu Gorantla, a full-stack engineer with a focus on backend development, cloud infrastructure, and building scalable systems.&lt;/p&gt;
&lt;h2 id="what-i-write-about"&gt;What I Write About&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;&lt;strong&gt;Python &amp;amp; Django&lt;/strong&gt; - Web development, APIs, and best practices&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Kubernetes &amp;amp; DevOps&lt;/strong&gt; - Container orchestration, CI/CD, and infrastructure&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;System Architecture&lt;/strong&gt; - Distributed systems, databases, and performance&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Backend Engineering&lt;/strong&gt; - Design patterns, optimization, and tooling&lt;/li&gt;
&lt;/ul&gt;
&lt;h2 id="connect"&gt;Connect&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;&lt;a href="https://github.com/maheshbabugorantla"&gt;GitHub&lt;/a&gt;&lt;/li&gt;
&lt;li&gt;&lt;a href="https://linkedin.com/in/maheshbabugorantla"&gt;LinkedIn&lt;/a&gt;&lt;/li&gt;
&lt;/ul&gt;</description></item></channel></rss>