> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/gym/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/gym/_mcp/server.

# Example Resources Servers

> Concrete Resources Servers and the task, action, and verification patterns they demonstrate.

Resources Servers can model anything from a stateful workplace simulation to an isolated code execution sandbox. These examples show the shape of real server implementations and how task setup, tool actions, and verification fit together.

## `workplace_assistant`

[`workplace_assistant`](https://github.com/NVIDIA-NeMo/Gym/tree/main/resources_servers/workplace_assistant) implements multi-step tool calling in a workplace setting.

* **Task**: Execute business activities such as sending emails, scheduling meetings, and managing projects.
* **Actions**: 26 tools across 5 databases: email, calendar, analytics, project management, and CRM. Each tool can read and mutate the database state.
* **Verification**: State matching: executes both the agent's actions and the ground truth actions against fresh databases, then compares the resulting states.

## `math_with_code`

[`math_with_code`](https://github.com/NVIDIA-NeMo/Gym/tree/main/resources_servers/math_with_code) implements mathematical reasoning with code execution.

* **Task**: Solve math problems using Python as a reasoning tool.
* **Actions**: `execute_python()` runs code in an isolated per-session process with numpy, scipy, and pandas available. State persists across steps so the agent can build on previous computations.
* **Verification**: Answer correctness: extracts the boxed answer from the model's final response and compares it against the expected result.

Review the Resources Server role, state model, tool endpoints, and verifier interface.

Build a minimal environment with a custom Resources Server.