Back to Articles
Agents are everywhere, and we want to ensure that the Hugging Face Hub is a great home for them! So one of my first tasks after joining Hugging Face is to make sure coding agents actually succeed when they reach for our cloud partner integrations, and here you can find a write-up on what I found as I went through it along with agents. This post is about what happened when I asked the most popular coding agents to deploy an LLM on Amazon SageMaker. In the next posts I'll show you how to teach your agents to do real AI work on your favorite cloud. Follow me to catch them when they land!
Deploying a Hugging Face model to SageMaker is mostly repetitive work. The steps barely change from one model to the next, which is exactly the kind of thing you'd want to hand off to a coding agent. In theory you point an agent at a model ID on the Hub, walk away, and come back to a working endpoint. I wanted to see how well that actually holds up, so I gave the job to Claude Code running Opus 4.8, which per the Hub's own agent usage data is the agent most people use to work with Hugging Face right now. And I watched the entire run rather than just checking the endpoint at the end. Spoiler, it did not go well.
