Stop Giving Your Agent Tools. Give It a Sandbox - Mikyo King, Arize AI
Source
youtube.com
Author
AI Engineer
Date
Why it matters
Replacing a large tool catalog with a sandboxAn isolated environment where AI-generated code or agent actions run without being able to touch anything real.Full definition → where the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → composes tools in code cut tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → by 43% and cost by 31% in Arize's Harbor evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition →, with the tradeoffs around secrets and permissions spelled out.
Terms in this piece · Glossary
sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
videoWho Is Making This Request? Agent Auth 101 - Kamil Potrec, Keycard
videoStop Guessing Your vLLM Config: Benchmarking LLMs on Runpod - Chris Vela, Runpod
videoWe Kept Rebuilding Our AI Agent. Here's What Survived - Fuad Ali, Arize AI
videoExploits Now Beat Patches: Open Source Security in the AI Era - Patrick Smyth, Chainguard