---
title: 'Your agents need a sandbox, not a desert'
description: >-
  Everyone agrees agents need code execution. The agreement ends the moment you
  ask how. The usual answer is 'my agent needs a full Linux VM to succeed.' That
  answer suits sandbox providers, and it's often wrong.
date: '2026-07-29'
dateDisplay: 'Wed, Jul 29 · 3:30pm UTC (11:30am EDT)'
duration: 30 min
status: upcoming
tags:
  - Monty
  - Logfire
speakers:
  - Samuel Colvin
canonical: 'https://pydantic.dev/events/agents-need-a-sandbox-not-a-desert'
---

> Markdown version of [Your agents need a sandbox, not a desert](https://pydantic.dev/events/agents-need-a-sandbox-not-a-desert) — the canonical HTML page.
>
> Wed, Jul 29 · 3:30pm UTC (11:30am EDT) · 30 min · Speakers: [Samuel Colvin](https://pydantic.dev/authors/samuel-colvin.md)
>
> All events: [/events.md](https://pydantic.dev/events.md) · Site index: [/llms.txt](https://pydantic.dev/llms.txt)

---

# Your agents need a sandbox, not a desert

Everyone agrees agents need code execution. The agreement ends the moment you ask how. The usual answer is 'my agent needs a full Linux VM to succeed.' That answer suits sandbox providers, and it's often wrong.

## What you'll learn

- Why 'give the agent a full VM' is the wrong default for many agent workflows
- What agents actually need from code execution: safe, expressive compute, not a whole computer
- How Pydantic Monty, a minimal Python interpreter written in Rust, runs agent-written code without a full sandbox
- Where a curated runtime beats a full sandbox on complexity, cost, operational overhead, and latency

## About

Everyone agrees agents need code execution. The agreement ends the moment you ask how to do it. The usual answer is "my agent needs a full Linux VM to succeed." That answer suits sandbox providers, and it's often wrong.

Plenty of real-world agent workflows don't need a whole computer. No arbitrary packages, no shell access, no CPython or node, never mind `awk`, `sed`, and `gcc`. The model needs a small amount of safe, expressive compute: enough to write code, call tools, and keep intermediate state out of the context window. That's the idea behind Pydantic Monty, a minimal Python interpreter written in Rust and built for running code that agents write.

Samuel Colvin, founder and CEO of Pydantic, makes the case that for a large class of agent systems, a curated set of tools in a custom runtime beats a full sandbox. Not because full sandboxes are bad, but because they solve a much bigger problem than most embedded agents have, and you pay for the mismatch in complexity, cost, operational pain, and latency that can run 100,000 times higher. There's such a thing as too much sand. Often the limits of a small, custom-built sandbox are a feature, not a bug.

A 30-minute session, with time for your questions at the end.

## Register

Register on the event page: https://pydantic.dev/events/agents-need-a-sandbox-not-a-desert