How To Delegate To An Agent Like You Would An Employee?

<p><strong>OpenAI&#39;s Codex</strong> developer experience lead sits down with a former comedian turned ML engineering lead for a conversation about what happens when computer use agents stop being a novelty and start actually running your day.</p><p><br></p><p>The conversation moves through building an AI-powered morning brief that reads every email, Slack message, and tweet before you&#39;ve even opened your laptop, letting pinned threads check in on themselves every 30 minutes, and a skills system built to mirror how a person actually writes and reviews code. There&#39;s a close look at the guardrails and permission layers that keep an autonomous agent from pushing to the wrong repo or replying to the wrong tweet, how a codebase merging thousands of pull requests a day survives thanks to self-healing review before anything hits CI, and the idea of AI deference - when an agent should push through a task alone versus stop and ask for help. </p><p><br></p><p>The back half gets personal: why developing taste and vocabulary now matters more than working harder, what it actually takes to delegate to an agent the way you&#39;d onboard a new employee, and why this might be the year voice-orchestrated computer use finally makes everyone feel like they&#39;re talking to Jarvis.</p><p><br></p><p>OpenAI: <a href="https://openai.com" target="_blank" rel="ugc noopener noreferrer">https://openai.com</a></p><p>Monaco: <a href="https://www.monaco.com" target="_blank" rel="ugc noopener noreferrer">https://www.monaco.com</a></p><p><br></p><p>Jason Liu: <a href="https://www.linkedin.com/in/jxnlco" target="_blank" rel="ugc noopener noreferrer">https://www.linkedin.com/in/jxnlco</a></p><p>Mihail Eric: <a href="https://www.linkedin.com/in/mihaileric" target="_blank" rel="ugc noopener noreferrer">https://www.linkedin.com/in/mihaileric</a></p><p>Demetrios: <a href="https://www.linkedin.com/in/dpbrinkm" target="_blank" rel="ugc noopener noreferrer">https://www.linkedin.com/in/dpbrinkm</a></p><p><br></p><p>Timestamps:</p><p>[00:00] Intro and guest backgrounds</p><p>[01:36] Why computer use beats plain API calls </p><p>[09:11] Building an AI-powered morning brief </p><p>[10:17] Self-monitoring threads that check in on their own </p><p>[18:26] How OpenAI reviews thousands of PRs a day </p><p>[19:42] Self-healing pull requests before CI even runs </p><p>[23:07] Building review skills from teammates&#39; habits </p><p>[30:52] Why hard work stops being the differentiator </p><p>[35:03] Introducing the idea of AI deference </p><p>[42:44] Learning to delegate like hiring your first assistant </p><p>[46:22] Why voice beats typing for giving agents context </p><p>[50:56] The Tony Stark Jarvis analogy for this year</p>