<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Langchain on Aamer Paul</title>
    <link>https://aamernabi.github.io/tags/langchain/</link>
    <description>Recent content in Langchain on Aamer Paul</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 04 Oct 2025 21:53:45 +0530</lastBuildDate>
    <atom:link href="https://aamernabi.github.io/tags/langchain/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building an AI Email Assistant with Prompt Chaining and LangGraph</title>
      <link>https://aamernabi.github.io/posts/prompt-chaining-using-langgraph/</link>
      <pubDate>Sat, 04 Oct 2025 21:53:45 +0530</pubDate>
      <guid>https://aamernabi.github.io/posts/prompt-chaining-using-langgraph/</guid>
      <description>&lt;h2 id=&#34;introduction&#34;&gt;Introduction&lt;/h2&gt;&#xA;&lt;p&gt;Generative AI has unlocked solutions to problems previously considered impractical or even impossible to automate. Take email management, for example. The daily influx of client inquiries, meeting requests, and project updates, it can consume your entire workday. While simple AI solutions promise relief but they often fall short, generating generic and context-blind replies.&lt;/p&gt;&#xA;&lt;p&gt;In this article, we will move beyond  basic &amp;ldquo;one-shot&amp;rdquo; LLM prompts to build an intelligent email responder using &lt;strong&gt;Prompt Chaining&lt;/strong&gt;, &lt;strong&gt;Context Engineering&lt;/strong&gt;, and &lt;strong&gt;LangGraph&lt;/strong&gt; for robust orchestration. We will build a sophisticated multi-step workflow that:&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
