<p>AI now codes faster than most engineers but it also confidently makes stuff up. The “AI made me a 10x dev” story sounds great online, yet many AI-driven projects quietly collapse, and teams pretend they’re not using it. The real value isn’t writing code anymore; it’s steering AI, setting boundaries, and catching its mistakes. Without strong code review, AI becomes a liability. With it, it’s a massive accelerator. The gap is widening fast: structured AI teams are flying ahead, resistant ones are stuck. Today we’re breaking down the real wins, failures, and what coding actually looks like in 2026. In this episode:</p><p><br></p><ul><li>Our experiences with AI coding assistants;</li><li>How to do it wrong and how to do it right;</li><li>Context engineering: beyond prompt engineering;</li><li>The importance of tooling around the model;</li><li>How to implement this for your team and not break everything.</li></ul><p><br></p><p>Check out <a href="https://mkdev.me⁠" target="_blank" rel="ugc noopener noreferrer">our website</a> to learn more about the services mkdev offers for companies.</p><p>Subscribe to <a href="https://mkdev.me/dispatch⁠" target="_blank" rel="ugc noopener noreferrer">our newsletter</a>.</p><p>Buy mkdev merchandise <a href="https://store.mkdev.me⁠" target="_blank" rel="ugc noopener noreferrer">here</a>.</p><p><br></p><p><em>Podcast editing: </em><a href="https://www.instagram.com/red_sparks_production⁠" target="_blank" rel="ugc noopener noreferrer"><em>Mila Jones</em></a><em> / </em><a href="mailto:[email protected]" target="_blank" rel="ugc noopener noreferrer"><em>[email protected]</em></a><em></em></p>