<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:media="http://search.yahoo.com/mrss/" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <atom:link href="https://feeds.megaphone.fm/mainbranch" rel="self" type="application/rss+xml"/>
    <title>Main Branch</title>
    <link>https://www.categoryvc.com/</link>
    <language>en</language>
    <copyright></copyright>
    <description>Main Branch is a podcast about how leading AI startups get built, deployed, and scaled.

Each episode, host Cagla Kaymaz goes deep with AI founders and early adopters, covering their tech stack, research bets, inflection points, key hires, and more. Early guests include founders of Glean, CrewAI, LaunchDarkly, and Myriad AI.&amp;nbsp;

Cagla is a seed investor at Category VC, focused on AI infra, devtools, and apps. Before VC, she was an engineering and product leader at Microsoft, and holds math and CS degrees from Stanford.</description>
    <image>
      <url>https://megaphone.imgix.net/podcasts/1d4ae678-5df2-11f1-9ba5-f727307fc935/image/7f7bbb022ca76d85b322da23bd46f3fd.png?ixlib=rails-4.3.1&amp;max-w=3000&amp;max-h=3000&amp;fit=crop&amp;auto=format,compress</url>
      <title>Main Branch</title>
      <link>https://www.categoryvc.com/</link>
    </image>
    <itunes:type>episodic</itunes:type>
    <itunes:subtitle>Build. Deploy. Scale.</itunes:subtitle>
    <itunes:author>Cagla Kaymaz</itunes:author>
    <itunes:summary>Main Branch is a podcast about how leading AI startups get built, deployed, and scaled.

Each episode, host Cagla Kaymaz goes deep with AI founders and early adopters, covering their tech stack, research bets, inflection points, key hires, and more. Early guests include founders of Glean, CrewAI, LaunchDarkly, and Myriad AI.&amp;nbsp;

Cagla is a seed investor at Category VC, focused on AI infra, devtools, and apps. Before VC, she was an engineering and product leader at Microsoft, and holds math and CS degrees from Stanford.</itunes:summary>
    <content:encoded>
      <![CDATA[<p>Main Branch is a podcast about how leading AI startups get built, deployed, and scaled.</p>
<p>Each episode, host Cagla Kaymaz goes deep with AI founders and early adopters, covering their tech stack, research bets, inflection points, key hires, and more. Early guests include founders of Glean, CrewAI, LaunchDarkly, and Myriad AI.&nbsp;</p>
<p>Cagla is a seed investor at <a href="https://www.categoryvc.com/">Category VC</a>, focused on AI infra, devtools, and apps. Before VC, she was an engineering and product leader at Microsoft, and holds math and CS degrees from Stanford.</p>]]>
    </content:encoded>
    <itunes:owner>
      <itunes:name>Cagla Kaymaz</itunes:name>
      <itunes:email>contact@lightningpod.fm</itunes:email>
    </itunes:owner>
    <itunes:image href="https://megaphone.imgix.net/podcasts/1d4ae678-5df2-11f1-9ba5-f727307fc935/image/7f7bbb022ca76d85b322da23bd46f3fd.png?ixlib=rails-4.3.1&amp;max-w=3000&amp;max-h=3000&amp;fit=crop&amp;auto=format,compress"/>
    <itunes:category text="Technology">
    </itunes:category>
    <itunes:category text="Business">
    </itunes:category>
    <itunes:category text="News">
      <itunes:category text="Tech News"/>
    </itunes:category>
    <item>
      <title>How Agents Learn, Remember, and Improve Over Time, with João (Joe) Moura, CEO of CrewAI</title>
      <description>João (Joe) Moura built CrewAI into one of the most popular agent frameworks out there, with over 50,000 GitHub stars and running inside more than half of the Fortune 500.

Listen in as we get into whether frameworks are dead or just turning into harnesses, how agents learn and improve themselves, and why rising token costs are pushing enterprises toward open source and local models.



00:00 Introduction
01:45 What is CrewAI? + Frameworks vs Harnesses
05:42 AI Agents and the SaaSpocalypse
09:43 How AI Agents Use Memory and Self-Learning
14:41 Optimizing Context, Token Costs, and Local Models
19:44 Enterprise AI Use Cases and Agent Workshops
29:08 Why Use CrewAI Instead of Claude?
33:48 Community Building and the Vision for CrewAI
41:42 The Future of Open Source AI in 2050

 

Joe's LinkedIn: https://www.linkedin.com/in/joaomdmoura/

 

Cagla’s LinkedIn: https://www.linkedin.com/in/caglakaymaz/ 
Cagla’s X: https://x.com/caglakaymazLearn more about Category Ventures: https://www.categoryvc.com/
 
Produced and edited by Eric Johnson from LightningPod: https://lightningpod.fm/
 
Theme music composed by DJ La Mano, provided by https://soundtaxi.com/</description>
      <pubDate>Mon, 13 Jul 2026 11:00:00 -0000</pubDate>
      <itunes:episodeType>full</itunes:episodeType>
      <itunes:season>1</itunes:season>
      <itunes:episode>2</itunes:episode>
      <itunes:author>Cagla Kaymaz</itunes:author>
      <itunes:image href="https://megaphone.imgix.net/podcasts/ac82c6c2-7bb5-11f1-8104-e7f71b740108/image/18ed99e4e8335b73d52ce67d5a6ceca4.png?ixlib=rails-4.3.1&amp;max-w=3000&amp;max-h=3000&amp;fit=crop&amp;auto=format,compress"/>
      <itunes:subtitle></itunes:subtitle>
      <itunes:summary>João (Joe) Moura built CrewAI into one of the most popular agent frameworks out there, with over 50,000 GitHub stars and running inside more than half of the Fortune 500.

Listen in as we get into whether frameworks are dead or just turning into harnesses, how agents learn and improve themselves, and why rising token costs are pushing enterprises toward open source and local models.



00:00 Introduction
01:45 What is CrewAI? + Frameworks vs Harnesses
05:42 AI Agents and the SaaSpocalypse
09:43 How AI Agents Use Memory and Self-Learning
14:41 Optimizing Context, Token Costs, and Local Models
19:44 Enterprise AI Use Cases and Agent Workshops
29:08 Why Use CrewAI Instead of Claude?
33:48 Community Building and the Vision for CrewAI
41:42 The Future of Open Source AI in 2050

 

Joe's LinkedIn: https://www.linkedin.com/in/joaomdmoura/

 

Cagla’s LinkedIn: https://www.linkedin.com/in/caglakaymaz/ 
Cagla’s X: https://x.com/caglakaymazLearn more about Category Ventures: https://www.categoryvc.com/
 
Produced and edited by Eric Johnson from LightningPod: https://lightningpod.fm/
 
Theme music composed by DJ La Mano, provided by https://soundtaxi.com/</itunes:summary>
      <content:encoded>
        <![CDATA[<p>João (Joe) Moura built CrewAI into one of the most popular agent frameworks out there, with over 50,000 GitHub stars and running inside more than half of the Fortune 500.</p>
<p>Listen in as we get into whether frameworks are dead or just turning into harnesses, how agents learn and improve themselves, and why rising token costs are pushing enterprises toward open source and local models.</p>
<p><br></p>
<p>00:00 Introduction
01:45 What is CrewAI? + Frameworks vs Harnesses
05:42 AI Agents and the SaaSpocalypse
09:43 How AI Agents Use Memory and Self-Learning
14:41 Optimizing Context, Token Costs, and Local Models
19:44 Enterprise AI Use Cases and Agent Workshops
29:08 Why Use CrewAI Instead of Claude?
33:48 Community Building and the Vision for CrewAI
41:42 The Future of Open Source AI in 2050</p>
<p> </p>
<p>Joe's LinkedIn: <a href="https://www.linkedin.com/in/joaomdmoura/">https://www.linkedin.com/in/joaomdmoura/</a></p>
<p> </p>
<p>Cagla’s LinkedIn: <a href="https://www.linkedin.com/in/caglakaymaz/">https://www.linkedin.com/in/caglakaymaz/</a> 
Cagla’s X: <a href="https://x.com/caglakaymaz">https://x.com/caglakaymaz</a><br>Learn more about Category Ventures: <a href="https://www.categoryvc.com/">https://www.categoryvc.com/</a>
 
Produced and edited by Eric Johnson from LightningPod: <a href="https://lightningpod.fm/">https://lightningpod.fm/</a>
 
Theme music composed by DJ La Mano, provided by <a href="https://soundtaxi.com/">https://soundtaxi.com/</a></p>]]>
      </content:encoded>
      <itunes:duration>2701</itunes:duration>
      <guid isPermaLink="false"><![CDATA[ac82c6c2-7bb5-11f1-8104-e7f71b740108]]></guid>
      <enclosure url="https://traffic.megaphone.fm/NOTDI5848620604.mp3" length="0" type="audio/mpeg"/>
    </item>
    <item>
      <title>Arvind Jain’s AI Playbook: How The Glean CEO Built to $300M ARR</title>
      <description>For the launch episode of Main Branch, I sit down with Arvind Jain, founder and CEO of Glean, who took a widely dismissed idea and turned it into one of the fastest-growing AI platforms, crossing $300M in ARR.

We chat about how he built conviction when the enterprise search market was a graveyard, the three shifts (SaaS, cloud, and BERT-era transformers) that quietly made the problem solvable in 2019, and how the launch of LLMs and every step-function change from the labs since has been a lucky supercharger for Glean.

We trace the product arc from a search box to an agentic coworker, and dig into the early operating playbook, including how he used to send 100 cold LinkedIn DMs a day. Arvind makes the case for how to compete when foundation labs move up the stack, and why the AI market is still 100x undersupplied.

Chapters:
00:00 Introduction
02:12 Early Conviction in Enterprise Search
05:33 Why Previous Search Solutions Failed
07:42 From Transformers to Generative AI
14:24 The Scale of the AI Revolution
16:17 Competitive Moats and Strategic Focus
18:31 Advice for Founders Starting Today
21:24 The Multi-Year Stealth Journey
24:04 Early Sales Philosophy and Customer Discovery
29:38 Integrating AI at Glean
32:31 Hiring and Testing AI Aptitude
36:40 Embracing Market Challenges and Mission

Arvind's LinkedIn

Cagla’s LinkedIn 
Cagla’s XLearn more about Category Ventures

Produced and edited by Eric Johnson from LightningPod

Theme music composed by DJ La Mano, provided by Soundtaxi</description>
      <pubDate>Thu, 04 Jun 2026 11:00:00 -0000</pubDate>
      <itunes:episodeType>full</itunes:episodeType>
      <itunes:season>1</itunes:season>
      <itunes:episode>1</itunes:episode>
      <itunes:author>Cagla Kaymaz</itunes:author>
      <itunes:image href="https://megaphone.imgix.net/podcasts/74f4d8d2-5df4-11f1-bbb4-03e5d5459ba1/image/6b0baa4f4d3dcdb664726130c66caee6.png?ixlib=rails-4.3.1&amp;max-w=3000&amp;max-h=3000&amp;fit=crop&amp;auto=format,compress"/>
      <itunes:subtitle></itunes:subtitle>
      <itunes:summary>For the launch episode of Main Branch, I sit down with Arvind Jain, founder and CEO of Glean, who took a widely dismissed idea and turned it into one of the fastest-growing AI platforms, crossing $300M in ARR.

We chat about how he built conviction when the enterprise search market was a graveyard, the three shifts (SaaS, cloud, and BERT-era transformers) that quietly made the problem solvable in 2019, and how the launch of LLMs and every step-function change from the labs since has been a lucky supercharger for Glean.

We trace the product arc from a search box to an agentic coworker, and dig into the early operating playbook, including how he used to send 100 cold LinkedIn DMs a day. Arvind makes the case for how to compete when foundation labs move up the stack, and why the AI market is still 100x undersupplied.

Chapters:
00:00 Introduction
02:12 Early Conviction in Enterprise Search
05:33 Why Previous Search Solutions Failed
07:42 From Transformers to Generative AI
14:24 The Scale of the AI Revolution
16:17 Competitive Moats and Strategic Focus
18:31 Advice for Founders Starting Today
21:24 The Multi-Year Stealth Journey
24:04 Early Sales Philosophy and Customer Discovery
29:38 Integrating AI at Glean
32:31 Hiring and Testing AI Aptitude
36:40 Embracing Market Challenges and Mission

Arvind's LinkedIn

Cagla’s LinkedIn 
Cagla’s XLearn more about Category Ventures

Produced and edited by Eric Johnson from LightningPod

Theme music composed by DJ La Mano, provided by Soundtaxi</itunes:summary>
      <content:encoded>
        <![CDATA[<p>For the launch episode of Main Branch, I sit down with Arvind Jain, founder and CEO of Glean, who took a widely dismissed idea and turned it into one of the fastest-growing AI platforms, crossing $300M in ARR.</p>
<p>We chat about how he built conviction when the enterprise search market was a graveyard, the three shifts (SaaS, cloud, and BERT-era transformers) that quietly made the problem solvable in 2019, and how the launch of LLMs and every step-function change from the labs since has been a lucky supercharger for Glean.</p>
<p>We trace the product arc from a search box to an agentic coworker, and dig into the early operating playbook, including how he used to send 100 cold LinkedIn DMs a day. Arvind makes the case for how to compete when foundation labs move up the stack, and why the AI market is still 100x undersupplied.</p>
<p>Chapters:
00:00 Introduction
02:12 Early Conviction in Enterprise Search
05:33 Why Previous Search Solutions Failed
07:42 From Transformers to Generative AI
14:24 The Scale of the AI Revolution
16:17 Competitive Moats and Strategic Focus
18:31 Advice for Founders Starting Today
21:24 The Multi-Year Stealth Journey
24:04 Early Sales Philosophy and Customer Discovery
29:38 Integrating AI at Glean
32:31 Hiring and Testing AI Aptitude
36:40 Embracing Market Challenges and Mission</p>
<p><a href="https://www.linkedin.com/in/jain-arvind/">Arvind's LinkedIn</a></p>
<p><a href="https://www.linkedin.com/in/caglakaymaz/">Cagla’s LinkedIn</a> <br>
<a href="https://x.com/caglakaymaz%20%20">Cagla’s X</a><br><a href="https://www.categoryvc.com/">Learn more about Category Ventures</a></p>
<p>Produced and edited by Eric Johnson from <a href="https://lightningpod.fm/">LightningPod</a></p>
<p>Theme music composed by DJ La Mano, provided by <a href="https://soundtaxi.com/">Soundtaxi</a></p>]]>
      </content:encoded>
      <itunes:duration>2524</itunes:duration>
      <guid isPermaLink="false"><![CDATA[74f4d8d2-5df4-11f1-bbb4-03e5d5459ba1]]></guid>
      <enclosure url="https://traffic.megaphone.fm/NOTDI1100527078.mp3" length="0" type="audio/mpeg"/>
    </item>
  </channel>
</rss>
