AI agents are everywhere in the conversation, but their real value is harder to pin down. The promise is simple: systems that can take a goal, plan steps, and adapt with minimal oversight. The challenge is knowing when that promise pays off and when it doesn’t.

In this talk we’ll look at how to extract value from agentic systems. We’ll cover what makes an AI agent useful, why you might choose one over simpler automation, and the challenges that come with autonomy. We’ll show how tool use and protocols like MCP fit into the picture, and close with testing and evaluation: how to measure whether an agent is doing real work or just burning dollars.

Learning outcomes:
* Identify where AI agents provide leverage over traditional automation
* Recognize tradeoffs in autonomy and tool use
* Evaluate whether an agent is delivering value
* Anticipate common failure modes in agent implementations

I have given this talk previously at dev up 2025