Technology1 min read

Run Scale AI’s AgentEnv evals on Vercel Sandbox

By · Published by Everything Blog

In short

AgentEnv, a testing framework for Scale AI, is now available on Vercel Sandbox, allowing for separate task and agent environments. The example and command for running an evaluation are provided, with instructions for replacing team and project details.

Key points

  • Available on Vercel Sandbox for task and agent separation.: Available on Vercel Sandbox for task and agent separation.
  • Example and command provided for running an evaluation.: Example and command provided for running an evaluation.
  • Replace team and project details with actual values.: Replace team and project details with actual values.

Sources checked by our analysis pipeline: 1

AgentEnv, Scale AI's framework for testing agents against tasks and scoring their results, now runs on Vercel Sandbox. The Vercel provider ships in AgentEnv 0.9.1334 and later, and runs the agent and its task environment in separate Sandboxes.

Try the AgentEnv example to run an evaluation on Vercel Sandbox and inspect the task’s score and the agent’s recorded actions. After completing the setup guide, run this command from the cloned repository. It uses your existing Vercel CLI login:

./vercel-eval --scope YOUR_TEAM --project YOUR_PROJECT

Replace YOUR_TEAM

with your Vercel team slug and YOUR_PROJECT

with an existing project name.

Learn more in the Sandbox ecosystem documentation.

Original source: vercel.com

Technology