> For the complete documentation index, see [llms.txt](https://docs.stg.ai.neevcloud.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stg.ai.neevcloud.com/agentic-studio/overview.md).

# Sandbox

Sandbox gives you on-demand, isolated compute environments that you can spin up in seconds. You can choose a base template, configure your resources, and get a fully provisioned environment ready to run AI agents and code - without any infrastructure setup or long-term commitment.

With Sandbox, you can quickly experiment, build, and deploy in a controlled environment while maintaining flexibility and efficiency.

## What You Can Build with Sandbox

Sandbox are designed for running autonomous AI agents and code execution workloads in secure, isolated environments. Here's what you can build and run with them:

* Run AI agents in isolated environments without affecting your local machine or production infrastructure
* Execute untrusted or user-generated code safely inside a contained sandbox
* Spin up fresh environments for every agent run and tear them down when done
* Capture filesystem state with snapshots and restore or fork environments for reproducible agent runs
* Pause sandboxes between runs to stop billing while preserving your working state on disk
* Build and test multi-agent pipelines with dedicated compute resources for each agent

## Sandbox Dashboard

When you open Agentic Studio from the left sidebar and navigate to Overview, you see a real-time summary of your sandbox pool:

* **Total Sandboxes** – Total number of sandboxes in the selected project, across all states
* **Ready** – Number of sandboxes that are healthy and reachable
* **Needs Attention** – Sandboxes that require action, such as failed provisioning
* **Templates** – Available base images, including standard and browser templates

## Sandbox Templates

Every sandbox is created from a template. A template defines the base operating system and pre-installed tooling your sandbox starts with. NeevCloud provides the following default templates:

| Template               | Type     | Description                                                              |
| ---------------------- | -------- | ------------------------------------------------------------------------ |
| `debian-12-minimal`    | Standard | Lightweight Debian 12 base for general-purpose agent workloads           |
| `ubuntu-24.04-minimal` | Standard | Ubuntu 24.04 minimal base, stable and widely supported                   |
| `ubuntu-26.04-minimal` | Standard | Ubuntu 26.04 minimal base, recommended for most agent sandboxes          |
| `ubuntu-26.04-systemd` | Standard | Ubuntu 26.04 with systemd, for workloads that require service management |
| `ubuntu-26.04-vnc`     | Browser  | Ubuntu 26.04 with VNC, for web-based and browser agent tasks             |

**Tip:** Use `ubuntu-26.04-minimal` as your default. It is the most general-purpose template and works for the majority of AI agent and code execution workloads.

## Real-World Use Cases

The following examples demonstrate how Agentic Studio sandbox can be used across different industries and workloads:

* **AI Customer Support Agents** - Run support agents that retrieve knowledge base articles, analyze customer queries, and generate responses in isolated environments.
* **Software Engineering Agents** - Execute code, run tests, analyze repositories, and automate development workflows without impacting production systems.
* **Document Processing & Analysis** - Process contracts, invoices, reports, and PDFs to extract structured information and generate summaries.
* **Financial & Business Intelligence Workflows** - Analyze spreadsheets, generate reports, and perform data processing tasks in secure, dedicated environments.
* **Research & Data Collection Agents** - Gather, process, and analyze information from multiple sources while maintaining execution isolation.
* **Code Execution Platforms** - Safely run user-submitted code for educational platforms, coding assessments, AI copilots, and developer tools.
* **Multi-Agent Systems** - Coordinate multiple AI agents where separate sandbox handle planning, execution, validation, and reporting tasks.
* **DevOps & Automation Pipelines** - Execute infrastructure automation, deployment validation, compliance checks, and operational workflows in reproducible environments.