In this bonus episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss their hands-on experience with an AI agent for updating their podcast website. They share the AI's initial success, followed by its struggle with a more complex task, leading to valuable insights. Key takeaways include the importance of knowing when to reset the AI, providing clear instructions, and the need for strong QA practices. They also touch on personal approaches to problem-solving and the balance between AI assistance and human oversight.

Watch the full video of their coding experiment on our YouTube Channel.

• 00:00 Introduction and Welcome
• 00:27 AI Coding Experiment
• 00:58 Challenges with AI Assistance
• 04:21 Human vs AI Problem Solving
• 05:40 Trust and Familiarity with Code
• 10:20 QA and Error Handling
• 12:04 Conclusion and Sign-off