OpenAI

OpenAI Integration

Your agents can use OpenAI to search for information online, create and edit images, and run calculations - all without you needing to learn any tools yourself.

what your agents can do

Everything they can do.

Your agents have 7 capabilities in OpenAI. Here's what they can do.

Code and calculations

Code Interpreter (Python)

Execute Python code in a sandboxed environment using OpenAI's code interpreter.

Creating images

Image Combine

Combine multiple images into a single composition using OpenAI's GPT Image model.

Image Create

Generate images from text prompts using OpenAI's GPT Image model.

Editing images

Image Edit

Edit images with text instructions using OpenAI's GPT Image model.

Image Inpaint

Inpaint (edit specific areas) of images using a mask with OpenAI's GPT Image model.

Remove Background

Remove the background from images using OpenAI's GPT Image model.

Web search and browsing

Web Search

Search the web for current information using OpenAI's web search tool.

in practice

"Find the latest industry stats, create a chart comparing our performance, and put together a summary image for the next team meeting."

also available

Anthropic

Research, browse, and analyse

View Anthropic

also available

Google Vertex

Search, images, maps, and video - powered by Google Cloud

View Google Vertex