<?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>Youtube on ayyzenn</title><link>https://ayyzenn.github.io/tags/youtube/</link><description>Recent content in Youtube on ayyzenn</description><generator>Hugo -- 0.163.3</generator><language>en-us</language><lastBuildDate>Fri, 06 Jun 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://ayyzenn.github.io/tags/youtube/index.xml" rel="self" type="application/rss+xml"/><item><title>YouTube Summarizer: What I Built with LangGraph and Gemini</title><link>https://ayyzenn.github.io/posts/agent/</link><pubDate>Fri, 06 Jun 2025 00:00:00 +0000</pubDate><guid>https://ayyzenn.github.io/posts/agent/</guid><description>&lt;h2 id="what-i-built"&gt;What I Built&lt;/h2&gt;
&lt;p&gt;I wanted to paste a YouTube URL and get a summary — or ask questions about the video — without watching the whole thing. This project uses &lt;strong&gt;LangGraph&lt;/strong&gt; for the workflow and &lt;strong&gt;Gemini&lt;/strong&gt; for the actual summarizing and Q&amp;amp;A.&lt;/p&gt;
&lt;hr&gt;
&lt;h2 id="key-features-of-agentic-workflows"&gt;Key Features of Agentic Workflows&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;&lt;strong&gt;Modularity&lt;/strong&gt; — each step can be built and tested on its own&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;State&lt;/strong&gt; — data flows from step to step in a structured way&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Reusability&lt;/strong&gt; — the same steps can be reused in other projects&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Autonomy&lt;/strong&gt; — each step can decide what to do based on the input it receives&lt;/li&gt;
&lt;/ul&gt;
&lt;hr&gt;
&lt;h2 id="popular-tools-for-agentic-workflows"&gt;Popular Tools for Agentic Workflows&lt;/h2&gt;
&lt;table&gt;
&lt;thead&gt;
&lt;tr&gt;
&lt;th&gt;Tool&lt;/th&gt;
&lt;th&gt;Description&lt;/th&gt;
&lt;th&gt;Language&lt;/th&gt;
&lt;th&gt;Best For&lt;/th&gt;
&lt;/tr&gt;
&lt;/thead&gt;
&lt;tbody&gt;
&lt;tr&gt;
&lt;td&gt;&lt;strong&gt;LangGraph&lt;/strong&gt;&lt;/td&gt;
&lt;td&gt;Graph-based AI workflow framework with state management.&lt;/td&gt;
&lt;td&gt;Python&lt;/td&gt;
&lt;td&gt;Custom step-by-step pipelines&lt;/td&gt;
&lt;/tr&gt;
&lt;tr&gt;
&lt;td&gt;&lt;strong&gt;CrewAI&lt;/strong&gt;&lt;/td&gt;
&lt;td&gt;Agent orchestration tool inspired by human teams and role delegation.&lt;/td&gt;
&lt;td&gt;Python&lt;/td&gt;
&lt;td&gt;Role-based agent collaboration&lt;/td&gt;
&lt;/tr&gt;
&lt;tr&gt;
&lt;td&gt;&lt;strong&gt;Autogen&lt;/strong&gt;&lt;/td&gt;
&lt;td&gt;Microsoft&amp;rsquo;s multi-agent framework for goal-oriented dialogue and tasks.&lt;/td&gt;
&lt;td&gt;Python&lt;/td&gt;
&lt;td&gt;Conversational multi-agent systems&lt;/td&gt;
&lt;/tr&gt;
&lt;tr&gt;
&lt;td&gt;&lt;strong&gt;LangChain&lt;/strong&gt;&lt;/td&gt;
&lt;td&gt;General framework for chaining LLMs with tools, memory, and logic.&lt;/td&gt;
&lt;td&gt;Python&lt;/td&gt;
&lt;td&gt;Broader LLM apps beyond just agents&lt;/td&gt;
&lt;/tr&gt;
&lt;tr&gt;
&lt;td&gt;&lt;strong&gt;AgentOps&lt;/strong&gt;&lt;/td&gt;
&lt;td&gt;Infra layer for deploying and monitoring agentic systems.&lt;/td&gt;
&lt;td&gt;Platform&lt;/td&gt;
&lt;td&gt;Scaling, testing, and managing agents&lt;/td&gt;
&lt;/tr&gt;
&lt;/tbody&gt;
&lt;/table&gt;
&lt;hr&gt;
&lt;h2 id="why-i-chose-langgraph"&gt;Why I Chose LangGraph&lt;/h2&gt;
&lt;p&gt;For this project, I chose &lt;strong&gt;LangGraph&lt;/strong&gt; because:&lt;/p&gt;</description></item></channel></rss>