Training TutorialsNeMo RL

About Workplace Assistant

View as Markdown

Workplace Assistant is a multi-step agentic tool-use training environment that tests a model’s ability to execute business tasks in a simulated workplace setting.

Goal: Understand the training environment and how tasks are structured and verified.

Time: ~10 minutes (read)

In this section, you will learn:

  1. How tasks are structured for multi-step tool calling
  2. The available databases and tools
  3. How the environment verifies task completion
← Back to Tutorial Overview

Prerequisites

How the Model Completes Tasks

For each task, the model must:

  1. Understand the user’s intent from natural language
  2. Determine which tools to call and in what order
  3. Infer correct parameters (for example, look up email addresses or find matching customer records)
  4. Execute all necessary steps to complete the task

The model has up to 6 tool calling steps to accomplish each task.

Available Databases and Tools

Each task is a natural language request that the model must complete using the available tools. All tasks share the same set of tools that allow the model to retrieve more information or perform actions. Each task instance uses isolated database instances so actions from different rollouts don’t interfere.

  • Databases: Email, Calendar, Analytics, Project Management, Customer Relationship Manager (CRM)
  • Tools: Distributed across these databases
  • Tasks: Common business activities (such as sending emails, scheduling meetings, and managing projects)

All tasks are available in the Workplace Assistant HuggingFace dataset.

Task Examples

User query: “Send an email to john.smith@atlas.com with the subject ‘Team Meeting’ and body ‘Let’s meet tomorrow at 2pm to discuss the project.’”

Expected tool call:

1email_send_email(
2    recipient="john.smith@atlas.com",
3    subject="Team Meeting",
4    body="Let's meet tomorrow at 2pm to discuss the project."
5)

The tool adds a new email to the emails database.

How Verification Works

The environment is implemented as a FastAPI-based resources server that executes tools and verification. It uses state-matching verification: instead of requiring exact tool sequences, it compares final database states.

  • Flexibility: Multiple valid solution paths exist for the same task
  • Robustness: Model can recover from mistakes mid-trajectory
  • Goal-oriented: Focuses on outcomes, not specific procedures

Next Steps

Now that you understand the Workplace Assistant environment, learn how to configure NeMo Gym for training:

Continue to Gym Configuration →