---
title: "Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents"
description: "NVIDIA Holoscan is a platform for real-time AI applications at the edge, and HoloHub provides reference applications and components. This post describes an engineer-guided workflow in which a coding agent builds a separate Python endoscopic tool segmentation application from the existing MONAI model, sample video, and Holoscan patterns. The Holoscan CLI, invoked through ./holohub, exposes shared commands for scaffolding, running, modes, tests, and benchmarking, while development skills and documentation guide the agent through project-specific operations. The application connects video replay, preprocessing, TensorRT inference, segmentation postprocessing, telemetry, and HoloViz visualization, with visual, smoke, and benchmark modes; the post reports that the CLI-plus-skills-plus-docs/examples configuration produced a separate application in 40 minutes using 11M tokens, and concludes that this combination offered the lowest resource overhead among the compared configurations."
---

# Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents

[NVIDIA](https://yomu.fyi/company/nvidia-developer-blog) · Elizabeth Goodman · Aug 19, 2026

**Type:** Tutorial

## Summary

NVIDIA Holoscan is a platform for real-time AI applications at the edge, and HoloHub provides reference applications and components. This post describes an engineer-guided workflow in which a coding agent builds a separate Python endoscopic tool segmentation application from the existing MONAI model, sample video, and Holoscan patterns. The Holoscan CLI, invoked through ./holohub, exposes shared commands for scaffolding, running, modes, tests, and benchmarking, while development skills and documentation guide the agent through project-specific operations. The application connects video replay, preprocessing, TensorRT inference, segmentation postprocessing, telemetry, and HoloViz visualization, with visual, smoke, and benchmark modes; the post reports that the CLI-plus-skills-plus-docs/examples configuration produced a separate application in 40 minutes using 11M tokens, and concludes that this combination offered the lowest resource overhead among the compared configurations.

## Context

The work investigates whether a general-purpose coding agent can use the same examples, documentation, and development tools as an engineer to build a real-time endoscopic tool segmentation application. The stated objective includes live segmentation-mask visualization, statistical analysis, runtime telemetry, and repeatable benchmarking while reusing an existing model and sample video without modifying its weights.

## Approach / What changed

The workflow divides the goal into smaller, reviewable iterations. An engineer sets goals and constraints; the agent inspects HoloHub examples, documentation, and development skills, uses the ./holohub CLI to scaffold, build, run, test, and benchmark the application, and the engineer reviews code, outputs, and tests before defining the next iteration. The implementation reuses Holoscan operators and adds application modes for visualization, smoke testing, and benchmarking.

## Takeaways

- The workflow uses small, verifiable iterations so code, outputs, and tests can inform the next engineering prompt and design decision.
- Benchmark mode processes 300 frames using Holoscan Data Flow Tracking and exports measurements and plots, making latency review more repeatable.
- In the comparison, CLI guidance, development skills, and documentation/examples produced a separate application in 40 minutes with 11M tokens; the other configurations used 15M and 20M tokens and had implementation or efficiency drawbacks.

**Tags:** [Developer Experience](https://yomu.fyi/topic/developer-experience), [LLMs](https://yomu.fyi/topic/llm), [Performance](https://yomu.fyi/topic/performance), [Python](https://yomu.fyi/topic/python), [Testing](https://yomu.fyi/topic/testing)

- Source: [NVIDIA](https://developer.nvidia.com/blog/developing-nvidia-holoscan-applications-with-cli-skills-and-ai-coding-agents)
- Source URL: https://developer.nvidia.com/blog/developing-nvidia-holoscan-applications-with-cli-skills-and-ai-coding-agents
- Ingested by Yomu: 2026-08-29T00:00:52.750Z

[Read original post](https://developer.nvidia.com/blog/developing-nvidia-holoscan-applications-with-cli-skills-and-ai-coding-agents)