<?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>ADK-Go on Learnings in IT</title>
    <link>https://sachinsu.github.io/tags/adk-go/</link>
    <description>Recent content in ADK-Go on Learnings in IT</description>
    <image>
      <title>Learnings in IT</title>
      <url>https://sachinsu.github.io/images/papermod-cover.png</url>
      <link>https://sachinsu.github.io/images/papermod-cover.png</link>
    </image>
    <generator>Hugo -- 0.161.1</generator>
    <language>en</language>
    <copyright>©</copyright>
    <lastBuildDate>Sun, 03 May 2026 01:00:00 +0530</lastBuildDate>
    <atom:link href="https://sachinsu.github.io/tags/adk-go/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Agentic Analytics: Supercharging Ad-hoc Analytics with Local LLMs</title>
      <link>https://sachinsu.github.io/posts/agentic_analytics/</link>
      <pubDate>Sun, 03 May 2026 01:00:00 +0530</pubDate>
      <guid>https://sachinsu.github.io/posts/agentic_analytics/</guid>
      <description>&lt;h2 id=&#34;introduction&#34;&gt;Introduction&lt;/h2&gt;
&lt;p&gt;While much of the online discourse related to Generative AI is focussed on Automated code Generation. Lets look at alternate use case of it.&lt;br&gt;
Traditionally, Business Intelligence (BI) relies on custom-built dashboards and reports that query a data warehouse. This often requires heavy intervention from engineering teams to analyze requirements, develop artifacts, and maintain them over time.&lt;/p&gt;
&lt;p&gt;Imagine your data warehouse is built on a SQL-based DBMS with a custom web interface for analytics. Even with this setup, typical challenges remain:&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
