<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Productivity</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Productivity feed</description>
    <item>
      <title>Presentation: From Consumers to Builders: Turning 200 of our Team into Agent Creators in 2 Weeks</title>
      <link>https://www.infoq.com/presentations/building-internal-ai-agents/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</link>
      <description>&lt;img src="https://res.infoq.com/presentations/building-internal-ai-agents/en/mediumimage/medium-1790246283432.jpeg"/&gt;&lt;p&gt;Ben Maraney shares how Forter demystified AI agent creation for technical and non-technical staff. He discusses leveraging custom MCP servers, combining no-code and code-based platforms, sidestepping complex RAG setups, and aligning security and legal teams to accelerate internal agent adoption across R&amp;D.&lt;/p&gt; &lt;i&gt;By Ben Maraney&lt;/i&gt;</description>
      <category>Large language models</category>
      <category>Agents</category>
      <category>Compliance</category>
      <category>Transcripts</category>
      <category>AI Security</category>
      <category>Governance</category>
      <category>Productivity</category>
      <category>QCon AI Boston 2026</category>
      <category>Model Context Protocol (MCP)</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>presentation</category>
      <pubDate>Mon, 28 Sep 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/presentations/building-internal-ai-agents/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</guid>
      <dc:creator>Ben Maraney</dc:creator>
      <dc:date>2026-09-28T11:00:00Z</dc:date>
      <dc:identifier>/presentations/building-internal-ai-agents/en</dc:identifier>
    </item>
    <item>
      <title>Presentation: Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP</title>
      <link>https://www.infoq.com/presentations/linkedin-context-engineering/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</link>
      <description>&lt;img src="https://res.infoq.com/presentations/linkedin-context-engineering/en/mediumimage/ajay-prakash-medium-1789021803159.jpg"/&gt;&lt;p&gt;Ajay Prakash discusses how LinkedIn overcomes AI agent limitations in large codebases. He explains Contextual Agent Playbooks and Tools - built on Model Context Protocol (MCP) - which serves procedural memory, code search, and runbooks directly to coding agents. Prakash shares architectural details and operational guardrails that deliver a 20% productivity boost with zero loss in reliability.&lt;/p&gt; &lt;i&gt;By Ajay Prakash&lt;/i&gt;</description>
      <category>Agents</category>
      <category>LinkedIn</category>
      <category>Transcripts</category>
      <category>Productivity</category>
      <category>QCon AI Boston 2026</category>
      <category>AI Architecture</category>
      <category>Model Context Protocol (MCP)</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>presentation</category>
      <pubDate>Sat, 19 Sep 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/presentations/linkedin-context-engineering/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</guid>
      <dc:creator>Ajay Prakash</dc:creator>
      <dc:date>2026-09-19T11:00:00Z</dc:date>
      <dc:identifier>/presentations/linkedin-context-engineering/en</dc:identifier>
    </item>
    <item>
      <title>DoorDash Uses Multi Agent LLMs to Clean up 60,000 Feature Flags</title>
      <link>https://www.infoq.com/news/2026/09/doordash-feature-flag-cleanup/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/09/doordash-feature-flag-cleanup/en/headerimage/generatedHeaderImage-1788418529526.jpg"/&gt;&lt;p&gt;DoorDash built a multi-agent LLM system to automate stale feature flag cleanup across more than 60,000 flags and 623 repositories. The workflow combines live experimentation data through MCP, engineer approval, isolated Git worktrees, parallel agents, and automated validation. In an evaluation of 50 flags, 45 produced usable pull requests at an average of 13.8 minutes and $4.79 per cleanup.&lt;/p&gt; &lt;i&gt;By Leela Kumili&lt;/i&gt;</description>
      <category>Static Analysis</category>
      <category>Developer Experience</category>
      <category>A/B Testing</category>
      <category>Agents</category>
      <category>Feature Injection</category>
      <category>Experiment Driven Development</category>
      <category>github</category>
      <category>Feature Toggle</category>
      <category>Large language models</category>
      <category>git</category>
      <category>AI Coding</category>
      <category>AI Assisted Coding</category>
      <category>Productivity</category>
      <category>Automation</category>
      <category>AI Architecture</category>
      <category>Model Context Protocol (MCP)</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>DevOps</category>
      <category>Architecture &amp; Design</category>
      <category>Development</category>
      <category>news</category>
      <pubDate>Fri, 18 Sep 2026 13:50:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/09/doordash-feature-flag-cleanup/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</guid>
      <dc:creator>Leela Kumili</dc:creator>
      <dc:date>2026-09-18T13:50:00Z</dc:date>
      <dc:identifier>/news/2026/09/doordash-feature-flag-cleanup/en</dc:identifier>
    </item>
    <item>
      <title>Presentation: Complexity and Creativity in Software Engineering</title>
      <link>https://www.infoq.com/presentations/ai-software-engineering-complexity/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</link>
      <description>&lt;img src="https://res.infoq.com/presentations/ai-software-engineering-complexity/en/mediumimage/philip-mortimer-medium-1789021228203.jpeg"/&gt;&lt;p&gt;Phillip Mortimer discusses the shift toward write-only software driven by AI code generation. He explains why traditional pull requests are broken and shares how engineering leaders can manage complexity by decoupling intent from implementation, automating code reviews, and building self-healing architecture to unleash developer creativity across senior engineering and architecture teams.&lt;/p&gt; &lt;i&gt;By Phillip Mortimer&lt;/i&gt;</description>
      <category>Testing</category>
      <category>QCon London 2026</category>
      <category>AI Assisted Coding</category>
      <category>Management</category>
      <category>Transcripts</category>
      <category>Code Quality</category>
      <category>Productivity</category>
      <category>Leadership</category>
      <category>Architecture</category>
      <category>Culture &amp; Methods</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>presentation</category>
      <pubDate>Fri, 18 Sep 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/presentations/ai-software-engineering-complexity/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Productivity</guid>
      <dc:creator>Phillip Mortimer</dc:creator>
      <dc:date>2026-09-18T11:00:00Z</dc:date>
      <dc:identifier>/presentations/ai-software-engineering-complexity/en</dc:identifier>
    </item>
  </channel>
</rss>
