Inside the AWS Agent Toolkit with Liam Greenamyre

<p>Why do some teams see massive speedups from AI coding agents while others barely notice a difference? In this RedMonk New Builders Conversation with AWS, Kate Holterhoff talks with Liam Greenamyre, Principal PM of Developer Platforms at AWS, about the uneven impact of AI on software development and how to restructure work so agents can succeed. Liam explains why making tasks verifiable is the single biggest lever, then walks through the Agent Toolkit for AWS: a remote MCP server, 100+ skills, plugins, and a rules file that work with Claude Code, Codex, Kiro, and more. They dig into how a single RunScript tool covers 15,000+ AWS APIs token-efficiently, how IAM context keys separate human and agent actions, how agents discover new services like Aurora DSQL, and why isolated dev accounts make safe sandboxes for autonomous agents. Liam closes with a bold prediction: the biggest changes ahead are organizational, not technological.<br /><br />This New Builders conversation is sponsored by AWS.<br /><br />Show notes: <a href="https://redmonk.com/videos/liam-greenamyre/" rel="noopener noreferrer nofollow">https://redmonk.com/videos/liam-greenamyre/</a><br /><br />Chapters<br />00:04 Introduction to AI in Software Development<br />03:07 The Uneven Adoption of AI in Development Teams<br />06:20 Strategies for Successful AI Integration<br />10:09 Exploring the AWS Agent Toolkit<br />17:01 Guardrails and Context for AI Agents<br />20:10 The Impact of AI on FinOps and Cost Management<br />24:28 Evolution of Agent Tooling<br />32:17 Enhancing Discoverability in AWS<br />35:56 Guardrails and Safety in AWS Operations<br />41:03 Future of AI in Software Development</p>