Behind the Craft · Sunday, June 28, 2026
Jess Yan demonstrates an Anthropic Managed Agent configured for analysis on a fictitious grocery store dataset. The agent utilized a pre-built toolset, interacted with its file system, and produced three HTML files summarizing the analysis results after being given specific data schemas and task guidance.
“So here you see the core components of this agent. So one is model selection. Um, here's the system prompt, which is the raw text that the model gets to define its behavior, its guardrails, and, uh, high level awareness of the kinds of tests tasks that you will orchestrate to it.”
“I've given it access to a built-in tool set that we ship with every cloud managed agent. Um, and I've given it the ability to basically interact with its file system and produce, uh, produce results.”
“So, uh, basically the components are, there's a model, there's a prompt, right? There's tool access, and then there's skills, they're optional.”