Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents | NVIDIA Technical Blog
Aug 20, 2026Elizabeth Goodman

Summary
This post details the use of AI coding agents (specifically Codex with GPT-5.6) to develop a real-time endoscopic tool segmentation application using NVIDIA Holoscan and HoloHub. It describes an iterative development workflow where an engineer defines goals and constraints, and the AI agent uses the Holoscan CLI, HoloHub documentation, and development skills to implement, test, and benchmark the application. Key contributions include demonstrating an agent-guided workflow for creating a minimal working application, adding repeatable benchmarking modes (visual, smoke, benchmark) with data flow tracking, and showing how the combination of CLI, skills, and documentation leads to efficient development.
More from the Automated Model Fine-Tuning and Deployment with TAO Agent Skills trail
- Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages | NVIDIA Technical Blog
- AI Native by Design: Lessons Learned from Building NVIDIA TensorRT Model Connect | NVIDIA Technical Blog
- Evaluating AI Agent Skill Performance with NVIDIA SkillEvaluator | NVIDIA Technical Blog
- Start Customizing NVIDIA Nemotron 3 Nano with Prime Intellect Lab in Minutes | NVIDIA Technical Blog
- Lessons From the Leaderboard: What 5,000+ Kagglers Taught Us About Improving AI Reasoning | NVIDIA Technical Blog