The latest articles on DEV Community by Don Wedel (@donwedel). https://dev.to/donwedel https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4147934%2F8f0b358d-e968-4149-be87-1f0c7ad4da4a.jpg https://dev.to/donwedel en Don Wedel Fri, 09 Oct 2026 07:22:34 +0000 https://dev.to/donwedel/are-we-building-ai-agents-we-can-no-longer-control-2h1n https://dev.to/donwedel/are-we-building-ai-agents-we-can-no-longer-control-2h1n <p>AI agents are moving beyond generating code. They can now execute commands, modify files, browse the web, and coordinate with other agents.</p> <p>But here's the question: How much autonomy should we give an AI agent before the security risks outweigh the productivity gains?</p> <p>Should agents require human approval for every sensitive action, or should we trust them to operate independently within predefined boundaries?</p> <p><strong>I'm curious how other developers are approaching this in real-world projects.</strong></p> <p>Where do you draw the line between useful autonomy and dangerous overreach?</p> ai security devops programming Don Wedel Mon, 28 Sep 2026 19:19:15 +0000 https://dev.to/donwedel/lately-ive-been-thinking-about-how-quickly-ai-is-changing-software-development-were-moving-41dl https://dev.to/donwedel/lately-ive-been-thinking-about-how-quickly-ai-is-changing-software-development-were-moving-41dl