Learn with Me: Train AI Agents for Command-Line Tasks with Synthetic Data and RL | Nemotron Labs

​What if your computer-use agent could learn a new command-line tool like LangGraph CLI? Join us for a live “Learn with Me” with our NVIDIA AI research engineer, who will explore and debug in real time while teaching a BASH agent a brand new CLI tool with synthetic data and Reinforcement Learning with Verifiable Rewards (RLVR).

​Curious how it can be adapted for your own proprietary CLI environment? Join us live for a developer-focused livestream. In this interactive livestream, we’ll cover:

• ​A live demo: “Learn with Me” teaching your BASH agent a brand new CLI tool using a Nemotron model with NeMo Data Designer to design synthetic data, sending the agent to the Reinforcement Learning environment (NeMo Gym) with Unsloth GRPO, and running the agent with the new skill.

• ​Showcase how safety is built into every layer, from human-in-the-loop command approval to runtime isolation.

• ​Explain why synthetic data generation + RLVR/GRPO accelerate agent specialization for proprietary CLI environments without compromising accuracy or trust.

​Live Q&A throughout the livestream—bring your questions about the workflow, model customization, and synthetic data generation, and follow along as the engineer works through challenges in real time.

Join us at: Watch on YouTube