# How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces

DevFeed: [How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces](<https://devfeed.tech/articles/how-an-agent-built-a-3d-paris-gallery-by-chaining-two-hugging-face-spaces-7352.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/mishig/spaces-agents-md>)

Author: Mishig ᠮᠢᠰᠾᠢᠭ

Published: 2026-06-09T10:46:19Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [spaces](<https://devfeed.tech/topics/spaces.md>), [gradio](<https://devfeed.tech/topics/gradio.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [coding](<https://devfeed.tech/topics/coding.md>), [SDKs](<https://devfeed.tech/topics/sdks.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [building](<https://devfeed.tech/tags/building.md>), [coding](<https://devfeed.tech/tags/coding.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gradio](<https://devfeed.tech/tags/gradio.md>), [hub](<https://devfeed.tech/tags/hub.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [images](<https://devfeed.tech/tags/images.md>), [integration](<https://devfeed.tech/tags/integration.md>), [spaces](<https://devfeed.tech/tags/spaces.md>)

## AI overview

A coding agent builds a 3D gallery of Paris monuments by chaining two Hugging Face Spaces: one generates images and the other reconstructs 3D Gaussian splats. The article presents Gradio Spaces as documented, callable building blocks that agents can integrate into multimedia software pipelines.

## Source excerpt

I asked a coding agent to build a beautiful website showcasing the monuments of Paris as 3D Gaussian splats. I never opened an image generator. I never touched a 3D reconstruction tool. The agent produced every asset (the images and the 3D splats) by calling two Hugging Face Spaces directly, then wired them into a cinematic viewer.