<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" encoding="UTF-8" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/" xmlns:atom="http://www.w3.org/2005/Atom/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:fireside="http://fireside.fm/modules/rss/fireside">
  <channel>
    <fireside:hostname>app03</fireside:hostname>
    <fireside:genDate>Fri, 20 Nov 2026 04:21:09 +0000</fireside:genDate>
    <generator>Fireside (https://fireside.fm)</generator>
    <title>Software Defined Interviews - Episodes Tagged with “Ai Agents”</title>
    <link>https://www.softwaredefinedinterviews.com/tags/ai%20agents</link>
    <pubDate>Thu, 19 Nov 2026 20:00:00 +0100</pubDate>
    <description>Deep discussions about technology, enterprise IT, and the like</description>
    <language>en-us</language>
    <itunes:type>episodic</itunes:type>
    <itunes:subtitle>Deep discussions about technology, enterprise IT, and the like</itunes:subtitle>
    <itunes:author>Software Defined Talk</itunes:author>
    <itunes:summary>Deep discussions about technology, enterprise IT, and the like</itunes:summary>
    <itunes:image href="https://cdn.fireside.fm/file/fireside-images-2024/podcasts/images/7/752ee20c-8e7a-4ce1-8214-0a3fef88215c/cover.jpg?v=7"/>
    <itunes:explicit>yes</itunes:explicit>
    <itunes:owner>
      <itunes:name>Software Defined Talk</itunes:name>
      <itunes:email>softwaredefinedinterviews@cote.wtf</itunes:email>
    </itunes:owner>
<itunes:category text="Technology"/>
<itunes:category text="News">
  <itunes:category text="Tech News"/>
</itunes:category>
<itunes:category text="Business">
  <itunes:category text="Management"/>
</itunes:category>
<item>
  <title>Episode 131: Genius Fruit Flies, a Fake Company, and Agents That Delete the Logs, with D Niu</title>
  <link>https://www.softwaredefinedinterviews.com/131</link>
  <guid isPermaLink="false">7511f6f6-5ed3-4ba3-b189-8d2b91af89de</guid>
  <pubDate>Thu, 19 Nov 2026 20:00:00 +0100</pubDate>
  <author>Software Defined Talk</author>
  <enclosure url="https://aphid.fireside.fm/d/1437767933/752ee20c-8e7a-4ce1-8214-0a3fef88215c/7511f6f6-5ed3-4ba3-b189-8d2b91af89de.mp3" length="61275992" type="audio/mpeg"/>
  <itunes:episode>131</itunes:episode>
  <itunes:title>Genius Fruit Flies, a Fake Company, and Agents That Delete the Logs, with D Niu</itunes:title>
  <itunes:episodeType>full</itunes:episodeType>
  <itunes:author>Software Defined Talk</itunes:author>
  <itunes:subtitle>D Niu left Datadog to study how AI agents misbehave at work. She built a fake company to watch them, and found they leave behind infrastructure nobody else knows exists.</itunes:subtitle>
  <itunes:duration>1:02:29</itunes:duration>
  <itunes:explicit>yes</itunes:explicit>
  <itunes:image href="https://cdn.fireside.fm/file/fireside-images-2024/podcasts/images/7/752ee20c-8e7a-4ce1-8214-0a3fef88215c/episodes/7/7511f6f6-5ed3-4ba3-b189-8d2b91af89de/cover.jpg?v=1"/>
  <description>&lt;p&gt;D Niu spent almost five years in security research at Datadog, then left this summer to co-found Ontology Labs, which studies how AI agents misbehave doing ordinary work. She explains why she calls this summer's Hugging Face breakout a misalignment event rather than a hack, and how she built a fake eight-person company convincing enough that agents don't know they're in a test. Whitney and Coté ask why bigger models write more code than a simple task needs, and about what agents leave behind: API routes and database tables that never went through a deploy. Also: one model is a good intern, another a disgruntled senior engineer.&lt;/p&gt;

&lt;p&gt;You can watch &lt;a href="https://youtu.be/QqIKtcOt3aI" rel="nofollow noopener"&gt;the video of the recording&lt;/a&gt; as well, if you're into that kind of thing.&lt;/p&gt;

&lt;p&gt;Mentions:&lt;/p&gt;

&lt;ul&gt;
&lt;li&gt;&lt;a href="https://ontologyhq.ai/" rel="nofollow noopener"&gt;Ontology Labs&lt;/a&gt;, and &lt;a href="https://ontologyhq.ai/#labs" rel="nofollow noopener"&gt;its first set of research&lt;/a&gt;.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://misaligned.studio/" rel="nofollow noopener"&gt;misaligned.studio&lt;/a&gt;, D's earlier research on predicting agent behavior from tool calls.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.linkedin.com/in/dndndn/" rel="nofollow noopener"&gt;D on LinkedIn&lt;/a&gt;&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.alignmentforum.org/" rel="nofollow noopener"&gt;AI Alignment Forum&lt;/a&gt;, where D says the up-to-date research gets posted.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://exa.ai/" rel="nofollow noopener"&gt;Exa&lt;/a&gt;, the search engine that markets itself to agents.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.youtube.com/watch?v=SfaoDCn83bw" rel="nofollow noopener"&gt;Business!&lt;/a&gt;, Louie Zong's album of corporate music, now a two-episode favorite.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;Special Guest: D Niu.&lt;/p&gt;&lt;p&gt;Special Guest: D Niu.&lt;/p&gt;</description>
  <content:encoded>
    <![CDATA[<p>D Niu spent almost five years in security research at Datadog, then left this summer to co-found Ontology Labs, which studies how AI agents misbehave doing ordinary work. She explains why she calls this summer's Hugging Face breakout a misalignment event rather than a hack, and how she built a fake eight-person company convincing enough that agents don't know they're in a test. Whitney and Coté ask why bigger models write more code than a simple task needs, and about what agents leave behind: API routes and database tables that never went through a deploy. Also: one model is a good intern, another a disgruntled senior engineer.</p>

<p>You can watch <a href="https://youtu.be/QqIKtcOt3aI" rel="nofollow noopener">the video of the recording</a> as well, if you're into that kind of thing.</p>

<p>Mentions:</p>

<ul>
<li><a href="https://ontologyhq.ai/" rel="nofollow noopener">Ontology Labs</a>, and <a href="https://ontologyhq.ai/#labs" rel="nofollow noopener">its first set of research</a>.</li>
<li><a href="https://misaligned.studio/" rel="nofollow noopener">misaligned.studio</a>, D's earlier research on predicting agent behavior from tool calls.</li>
<li><a href="https://www.linkedin.com/in/dndndn/" rel="nofollow noopener">D on LinkedIn</a></li>
<li><a href="https://www.alignmentforum.org/" rel="nofollow noopener">AI Alignment Forum</a>, where D says the up-to-date research gets posted.</li>
<li><a href="https://exa.ai/" rel="nofollow noopener">Exa</a>, the search engine that markets itself to agents.</li>
<li><a href="https://www.youtube.com/watch?v=SfaoDCn83bw" rel="nofollow noopener">Business!</a>, Louie Zong's album of corporate music, now a two-episode favorite.</li>
</ul>

<p>Special Guest: D Niu.</p><p>Special Guest: D Niu.</p>]]>
  </content:encoded>
  <itunes:summary>
    <![CDATA[<p>D Niu spent almost five years in security research at Datadog, then left this summer to co-found Ontology Labs, which studies how AI agents misbehave doing ordinary work. She explains why she calls this summer's Hugging Face breakout a misalignment event rather than a hack, and how she built a fake eight-person company convincing enough that agents don't know they're in a test. Whitney and Coté ask why bigger models write more code than a simple task needs, and about what agents leave behind: API routes and database tables that never went through a deploy. Also: one model is a good intern, another a disgruntled senior engineer.</p>

<p>You can watch <a href="https://youtu.be/QqIKtcOt3aI" rel="nofollow noopener">the video of the recording</a> as well, if you're into that kind of thing.</p>

<p>Mentions:</p>

<ul>
<li><a href="https://ontologyhq.ai/" rel="nofollow noopener">Ontology Labs</a>, and <a href="https://ontologyhq.ai/#labs" rel="nofollow noopener">its first set of research</a>.</li>
<li><a href="https://misaligned.studio/" rel="nofollow noopener">misaligned.studio</a>, D's earlier research on predicting agent behavior from tool calls.</li>
<li><a href="https://www.linkedin.com/in/dndndn/" rel="nofollow noopener">D on LinkedIn</a></li>
<li><a href="https://www.alignmentforum.org/" rel="nofollow noopener">AI Alignment Forum</a>, where D says the up-to-date research gets posted.</li>
<li><a href="https://exa.ai/" rel="nofollow noopener">Exa</a>, the search engine that markets itself to agents.</li>
<li><a href="https://www.youtube.com/watch?v=SfaoDCn83bw" rel="nofollow noopener">Business!</a>, Louie Zong's album of corporate music, now a two-episode favorite.</li>
</ul>

<p>Special Guest: D Niu.</p><p>Special Guest: D Niu.</p>]]>
  </itunes:summary>
</item>
<item>
  <title>Episode 129: The Extinction of Enterprise Architects, Fifty Secrets Managers, and Deodorant Before AI, with Rick Clark</title>
  <link>https://www.softwaredefinedinterviews.com/129</link>
  <guid isPermaLink="false">e271897b-ccc4-4ce7-bcce-fa3ef46d454b</guid>
  <pubDate>Thu, 22 Oct 2026 12:00:00 +0200</pubDate>
  <author>Software Defined Talk</author>
  <enclosure url="https://aphid.fireside.fm/d/1437767933/752ee20c-8e7a-4ce1-8214-0a3fef88215c/e271897b-ccc4-4ce7-bcce-fa3ef46d454b.mp3" length="60377783" type="audio/mpeg"/>
  <itunes:episode>129</itunes:episode>
  <itunes:title>The Extinction of Enterprise Architects, Fifty Secrets Managers, and Deodorant Before AI, with Rick Clark</itunes:title>
  <itunes:episodeType>full</itunes:episodeType>
  <itunes:author>Software Defined Talk</itunes:author>
  <itunes:subtitle>Enterprise architecture is nearly extinct, and Rick Clark thinks fifteen years of shifting every decision left is what killed it. One insurance company he worked with ended up with over 50 secrets managers in production. His advice before you put AI anywhere near a mess like that: brush your teeth first.</itunes:subtitle>
  <itunes:duration>1:01:52</itunes:duration>
  <itunes:explicit>yes</itunes:explicit>
  <itunes:image href="https://cdn.fireside.fm/file/fireside-images-2024/podcasts/images/7/752ee20c-8e7a-4ce1-8214-0a3fef88215c/episodes/e/e271897b-ccc4-4ce7-bcce-fa3ef46d454b/cover.jpg?v=1"/>
  <description>&lt;p&gt;Rick Clark is Global Head of Cloud Advisory at UST, and co-founded OpenStack. His argument is that enterprise architecture is nearly extinct, killed off by fifteen years of shifting every decision left, and that this is how one insurance company he worked with ended up running over 50 secrets managers in production. Whitney and Coté push on whether platform engineering was meant to solve exactly that, and on what a modern enterprise architect would do instead - write the rules the platform enforces. The back half is agents: why nobody is ready to run them in production, and the difference between a rule an agent cannot break and one it must not break.&lt;/p&gt;

&lt;p&gt;You can watch &lt;a href="https://youtu.be/-Jjt9BaPAGE" rel="nofollow noopener"&gt;the video version of this episode&lt;/a&gt; as well, if you prefer that kind of thing.&lt;/p&gt;

&lt;p&gt;Mentions:&lt;/p&gt;

&lt;ul&gt;
&lt;li&gt;&lt;a href="https://www.linkedin.com/in/dendrobates/" rel="nofollow noopener"&gt;Rick on LinkedIn&lt;/a&gt;, which is where he sends people.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.linkedin.com/newsletters/the-construct-7469797981374984192" rel="nofollow noopener"&gt;The Construct&lt;/a&gt;, his newsletter on agentic workloads in production.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.thestack.technology/from-tokenmaxxing-to-tokenomics-youre-still-doing-it-wrong/" rel="nofollow noopener"&gt;From tokenmaxxing to tokenomics: you're still doing it wrong&lt;/a&gt;, his first op-ed for The Stack.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;Special Guest: Rick Clark.&lt;/p&gt;&lt;p&gt;Special Guest: Rick Clark.&lt;/p&gt;</description>
  <itunes:keywords>Rick Clark, UST, OpenStack, Ubuntu Server, Four Opens, enterprise architecture, enterprise architect, marchitecture, Ed McLaughlin, MasterCard, shift left, architectural coherence, cognitive load, platform engineering, Cloud Foundry, Kubernetes, Helm, Terraform, secrets management, governance as a service, PII, regulatory compliance, self-service platforms, developer productivity, developer flexibility, AI adoption, AI POCs, MIT study, agentic AI, agents in production, non-deterministic production, determinism, behavioral envelope, observability, tracing, fan-out graph, guardrails, must not versus cannot, Air Canada chatbot, OpenAI agent, AI ethics, regulators, auditors, CI/CD, intent-driven software, declarative intent, swarm of agents, build versus buy, Observability Engineering, SaaS, Salesforce, advisory work, The Construct, The Stack, tokenomics, Simon Wardley, SpringOne</itunes:keywords>
  <content:encoded>
    <![CDATA[<p>Rick Clark is Global Head of Cloud Advisory at UST, and co-founded OpenStack. His argument is that enterprise architecture is nearly extinct, killed off by fifteen years of shifting every decision left, and that this is how one insurance company he worked with ended up running over 50 secrets managers in production. Whitney and Coté push on whether platform engineering was meant to solve exactly that, and on what a modern enterprise architect would do instead - write the rules the platform enforces. The back half is agents: why nobody is ready to run them in production, and the difference between a rule an agent cannot break and one it must not break.</p>

<p>You can watch <a href="https://youtu.be/-Jjt9BaPAGE" rel="nofollow noopener">the video version of this episode</a> as well, if you prefer that kind of thing.</p>

<p>Mentions:</p>

<ul>
<li><a href="https://www.linkedin.com/in/dendrobates/" rel="nofollow noopener">Rick on LinkedIn</a>, which is where he sends people.</li>
<li><a href="https://www.linkedin.com/newsletters/the-construct-7469797981374984192" rel="nofollow noopener">The Construct</a>, his newsletter on agentic workloads in production.</li>
<li><a href="https://www.thestack.technology/from-tokenmaxxing-to-tokenomics-youre-still-doing-it-wrong/" rel="nofollow noopener">From tokenmaxxing to tokenomics: you're still doing it wrong</a>, his first op-ed for The Stack.</li>
</ul>

<p>Special Guest: Rick Clark.</p><p>Special Guest: Rick Clark.</p>]]>
  </content:encoded>
  <itunes:summary>
    <![CDATA[<p>Rick Clark is Global Head of Cloud Advisory at UST, and co-founded OpenStack. His argument is that enterprise architecture is nearly extinct, killed off by fifteen years of shifting every decision left, and that this is how one insurance company he worked with ended up running over 50 secrets managers in production. Whitney and Coté push on whether platform engineering was meant to solve exactly that, and on what a modern enterprise architect would do instead - write the rules the platform enforces. The back half is agents: why nobody is ready to run them in production, and the difference between a rule an agent cannot break and one it must not break.</p>

<p>You can watch <a href="https://youtu.be/-Jjt9BaPAGE" rel="nofollow noopener">the video version of this episode</a> as well, if you prefer that kind of thing.</p>

<p>Mentions:</p>

<ul>
<li><a href="https://www.linkedin.com/in/dendrobates/" rel="nofollow noopener">Rick on LinkedIn</a>, which is where he sends people.</li>
<li><a href="https://www.linkedin.com/newsletters/the-construct-7469797981374984192" rel="nofollow noopener">The Construct</a>, his newsletter on agentic workloads in production.</li>
<li><a href="https://www.thestack.technology/from-tokenmaxxing-to-tokenomics-youre-still-doing-it-wrong/" rel="nofollow noopener">From tokenmaxxing to tokenomics: you're still doing it wrong</a>, his first op-ed for The Stack.</li>
</ul>

<p>Special Guest: Rick Clark.</p><p>Special Guest: Rick Clark.</p>]]>
  </itunes:summary>
</item>
<item>
  <title>Episode 128: Animated Bedtime Stories, Telling Dummies What to Do, and Why Docker Lost, with Viktor Farcic</title>
  <link>https://www.softwaredefinedinterviews.com/128</link>
  <guid isPermaLink="false">b9411b79-5845-4b02-b993-be870eaeae8b</guid>
  <pubDate>Wed, 30 Sep 2026 07:00:00 +0200</pubDate>
  <author>Software Defined Talk</author>
  <enclosure url="https://aphid.fireside.fm/d/1437767933/752ee20c-8e7a-4ce1-8214-0a3fef88215c/b9411b79-5845-4b02-b993-be870eaeae8b.mp3" length="60909605" type="audio/mpeg"/>
  <itunes:episode>128</itunes:episode>
  <itunes:title>Animated Bedtime Stories, Telling Dummies What to Do, and Why Docker Lost, with Viktor Farcic</itunes:title>
  <itunes:episodeType>full</itunes:episodeType>
  <itunes:author>Software Defined Talk</itunes:author>
  <itunes:subtitle>Viktor Farcic makes animated bedtime stories about tech history because he decided people should not have to look at his face. He also runs 20 to 50 agents at once, has them argue with each other, and reviews their work off a private YouTube channel in the morning. Plus: why AI is cheap next to a salary, why he expects a bloodbath, and what actually went wrong at Docker.</itunes:subtitle>
  <itunes:duration>1:02:20</itunes:duration>
  <itunes:explicit>yes</itunes:explicit>
  <itunes:image href="https://cdn.fireside.fm/file/fireside-images-2024/podcasts/images/7/752ee20c-8e7a-4ce1-8214-0a3fef88215c/episodes/b/b9411b79-5845-4b02-b993-be870eaeae8b/cover.jpg?v=1"/>
  <description>&lt;p&gt;Viktor Farcic is a developer advocate at Upbound, runs the DevOps &amp;amp; AI Toolkit YouTube channel, and was last on the show back in episode 89. Whitney and Coté start with the animated bedtime stories he has started making - tech history told as fairy tales with a nightmare at the end - which he began after catching sight of himself in a mirror and deciding people should not have to watch that. From there it is what his working day looks like now, with 20 to 50 agents running at once, a coder and a tester and a reviewer who are not allowed to do each other's jobs and argue until they agree, and a private YouTube channel where the agents post recorded tests for him to review on his phone in the morning. The last stretch is money: why he thinks AI is cheap next to what a person costs, why he expects a bloodbath as industries fail to adapt, and a walk through Docker, Chef, Puppet, Ansible and HashiCorp on whether an open source company can ever turn a profit on its own.&lt;/p&gt;

&lt;p&gt;&lt;a href="https://youtu.be/bsART7GgK_0" rel="nofollow noopener"&gt;Check it out in YouTube&lt;/a&gt;, if you prefer that kind of thing.&lt;/p&gt;

&lt;p&gt;Mentions:&lt;/p&gt;

&lt;ul&gt;
&lt;li&gt;&lt;a href="https://www.youtube.com/@devopstoolkit" rel="nofollow noopener"&gt;DevOps &amp;amp; AI Toolkit on YouTube&lt;/a&gt;, where the bedtime stories live.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://devopstoolkit.live" rel="nofollow noopener"&gt;devopstoolkit.live&lt;/a&gt; - the blog and video archive.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://devopstoolkit.ai" rel="nofollow noopener"&gt;devopstoolkit.ai&lt;/a&gt; - the product.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://github.com/vfarcic" rel="nofollow noopener"&gt;Viktor on GitHub&lt;/a&gt;.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.devopsparadox.com" rel="nofollow noopener"&gt;DevOps Paradox&lt;/a&gt;, his other podcast.&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.softwaredefinedinterviews.com/89" rel="nofollow noopener"&gt;Episode 89&lt;/a&gt;, his first time on the show.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;Special Guest: Viktor Farcic.&lt;/p&gt;

&lt;p&gt;&lt;em&gt;Show notes written by AI with a human's lazy-look.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;Special Guest: Viktor Farcic.&lt;/p&gt;</description>
  <itunes:keywords>Viktor Farcic, Upbound, Crossplane, DevOps Toolkit, DevOps &amp; AI Toolkit, DevOps Paradox, AI agents, agentic AI, agent swarm, multi-agent, sub-agents, Claude, OpenCode, Greptile, Higgsfield, AI video generation, generated animation, bedtime stories, tech history, YouTube, content creation, developer advocacy, AI coding, specifications, spec-driven development, agent instructions, code review, automated testing, overnight agents, token cost, AI economics, cost of labour, job displacement, technical management, Docker, Solomon Hykes, Docker Swarm, Kubernetes, open source business model, Red Hat, HashiCorp, IBM, Ansible, Chef, Puppet, Pulumi, CFEngine, Terraform, configuration management, infrastructure as code, CNCF, Solo.io, acquisitions, IPO, FFmpeg, Descript, Anki</itunes:keywords>
  <content:encoded>
    <![CDATA[<p>Viktor Farcic is a developer advocate at Upbound, runs the DevOps &amp; AI Toolkit YouTube channel, and was last on the show back in episode 89. Whitney and Coté start with the animated bedtime stories he has started making - tech history told as fairy tales with a nightmare at the end - which he began after catching sight of himself in a mirror and deciding people should not have to watch that. From there it is what his working day looks like now, with 20 to 50 agents running at once, a coder and a tester and a reviewer who are not allowed to do each other's jobs and argue until they agree, and a private YouTube channel where the agents post recorded tests for him to review on his phone in the morning. The last stretch is money: why he thinks AI is cheap next to what a person costs, why he expects a bloodbath as industries fail to adapt, and a walk through Docker, Chef, Puppet, Ansible and HashiCorp on whether an open source company can ever turn a profit on its own.</p>

<p><a href="https://youtu.be/bsART7GgK_0" rel="nofollow noopener">Check it out in YouTube</a>, if you prefer that kind of thing.</p>

<p>Mentions:</p>

<ul>
<li><a href="https://www.youtube.com/@devopstoolkit" rel="nofollow noopener">DevOps &amp; AI Toolkit on YouTube</a>, where the bedtime stories live.</li>
<li><a href="https://devopstoolkit.live" rel="nofollow noopener">devopstoolkit.live</a> - the blog and video archive.</li>
<li><a href="https://devopstoolkit.ai" rel="nofollow noopener">devopstoolkit.ai</a> - the product.</li>
<li><a href="https://github.com/vfarcic" rel="nofollow noopener">Viktor on GitHub</a>.</li>
<li><a href="https://www.devopsparadox.com" rel="nofollow noopener">DevOps Paradox</a>, his other podcast.</li>
<li><a href="https://www.softwaredefinedinterviews.com/89" rel="nofollow noopener">Episode 89</a>, his first time on the show.</li>
</ul>

<p>Special Guest: Viktor Farcic.</p>

<p><em>Show notes written by AI with a human's lazy-look.</em></p><p>Special Guest: Viktor Farcic.</p>]]>
  </content:encoded>
  <itunes:summary>
    <![CDATA[<p>Viktor Farcic is a developer advocate at Upbound, runs the DevOps &amp; AI Toolkit YouTube channel, and was last on the show back in episode 89. Whitney and Coté start with the animated bedtime stories he has started making - tech history told as fairy tales with a nightmare at the end - which he began after catching sight of himself in a mirror and deciding people should not have to watch that. From there it is what his working day looks like now, with 20 to 50 agents running at once, a coder and a tester and a reviewer who are not allowed to do each other's jobs and argue until they agree, and a private YouTube channel where the agents post recorded tests for him to review on his phone in the morning. The last stretch is money: why he thinks AI is cheap next to what a person costs, why he expects a bloodbath as industries fail to adapt, and a walk through Docker, Chef, Puppet, Ansible and HashiCorp on whether an open source company can ever turn a profit on its own.</p>

<p><a href="https://youtu.be/bsART7GgK_0" rel="nofollow noopener">Check it out in YouTube</a>, if you prefer that kind of thing.</p>

<p>Mentions:</p>

<ul>
<li><a href="https://www.youtube.com/@devopstoolkit" rel="nofollow noopener">DevOps &amp; AI Toolkit on YouTube</a>, where the bedtime stories live.</li>
<li><a href="https://devopstoolkit.live" rel="nofollow noopener">devopstoolkit.live</a> - the blog and video archive.</li>
<li><a href="https://devopstoolkit.ai" rel="nofollow noopener">devopstoolkit.ai</a> - the product.</li>
<li><a href="https://github.com/vfarcic" rel="nofollow noopener">Viktor on GitHub</a>.</li>
<li><a href="https://www.devopsparadox.com" rel="nofollow noopener">DevOps Paradox</a>, his other podcast.</li>
<li><a href="https://www.softwaredefinedinterviews.com/89" rel="nofollow noopener">Episode 89</a>, his first time on the show.</li>
</ul>

<p>Special Guest: Viktor Farcic.</p>

<p><em>Show notes written by AI with a human's lazy-look.</em></p><p>Special Guest: Viktor Farcic.</p>]]>
  </itunes:summary>
</item>
  </channel>
</rss>
