Artifacts

What are Artifacts and how do I use them?

Artifacts allow AI models to share substantial, standalone content with you in a dedicated window separate from the main conversation. Artifacts make it easy to work with significant pieces of content that you may want to modify, build upon, or reference later.

When should I use Artifacts?

You should use Artifacts when the content you want to share has the following characteristics:

• It is significant and self-contained, typically consisting of over 15 lines of content.

• It is something you are likely to want to edit, iterate on, or reuse outside of the conversation.

• It represents a complex piece of content that stands on its own without requiring additional conversation context.

• It is content you are likely to want to refer back to or use later on

Some common examples of Artifact content include:

• Documents (Markdown or Plain Text)

• Code snippets

• Websites (single page HTML)

• Scalable Vector Graphics (SVG) images

• Diagrams and flowcharts

• Interactive React components

How do I use Artifacts?

To use Artifacts, you must turn on the toggle under the typing input bar.

Please note that not all language models support artifacts.

Currently, only Claude 3.5 Sonnet and GPT-4o support artifacts.

We plan to add artifact support to more models in the future.