Google Vertex

Google Vertex Integration

Your agents get access to Google's full toolkit - web search, image creation and editing, maps, and even video generation. Best for teams already using Google Cloud.

what your agents can do

Everything they can do.

Your agents have 14 capabilities in Google Vertex. Here's what they can do.

Code and calculations

Code Execution (Python)

Execute Python code using Google Vertex AI's built-in code execution tool.

Web search and browsing

Enterprise Web Search

Search the web using Google Vertex AI's Enterprise Web Search tool.

Google Search

Search the web using Google Vertex AI's built-in Google Search tool.

URL Context

Analyse a URL using Google Vertex AI's built-in URL Context tool.

Creating images

Gemini Image Combine

Combine multiple reference images into a new composition using Google's Gemini Image model.

Gemini Image Create

Generate images from text prompts using Google's Gemini Image model.

Editing images

Gemini Image Edit

Edit an existing image using text instructions with Google's Gemini Image model.

Location and search

Google Maps

Query Google Maps for location-based information using Vertex AI.

Creating videos

Veo Extend Video

Extend an existing video using Google's Veo model.

Veo Image-to-Video

Generate a video from a starting image using Google's Veo model.

Veo Image-to-Video (Last Frame)

Generate a video that transitions between two images using Google's Veo model.

Veo Mask Edit

Edit a video using a mask to add or remove objects.

Veo Reference Images

Generate video with style or asset references using Google's Veo model.

Veo Text-to-Video

Generate a video from a text prompt using Google's Veo model.

in practice

"Create a product video from our latest photos, generate social media images to match, and find local events we should sponsor."

also available

OpenAI

Search the web, create images, and run code

View OpenAI

also available

Anthropic

Research, browse, and analyse

View Anthropic