Resources · Make integration

Gemini Enterprise Agent Platform Make integrationAutomate Gemini Enterprise Agent Platform with Make.

Want Google's AI models to write, draw and describe inside your automations? The Gemini Enterprise Agent Platform Make integration gives you 7 action modules for text, images and video. This guide is for teams with a Google Cloud project: connect it, then build a first scenario.

Try the Gemini Enterprise Agent Platform integration on MakeSee the 7 modules

Verified Trustpilot reviews · AI, automation & growth agency

What you can automate

What does the Gemini Enterprise Agent Platform Make integration do?

It lets a Make scenario, the automation you build as a chain of bricks called modules, send work to Google's AI through your own Google Cloud project. A module asks for text, an image, a caption or a video, and the answer flows to the next app in the chain.

Product pictures that describe themselves. An online shop drops a new photo in its storage app, Generate an Image Caption writes the alt text, and the catalog is updated without anyone typing a word.

Support tickets that read screenshots. When a customer attaches a screenshot, Generate an Answer for an Image answers a precise question about it, such as which error message is visible, and the reply lands in the ticket for an agent to check.

Campaign visuals from a short brief. A marketer fills a form, Create a Chat Prompt (Gemini) turns the notes into a clear visual brief, then Generate an Image or Generate a Video produces the draft.

What Make does not do here: there is no trigger, so this app never starts a scenario on its own; another app or a schedule has to. Data received from Google APIs is handled under the Google API Services User Data Policy. The same kind of AI work can also be built in n8n; the n8n vs Make comparison lays out the differences, Make pricing explains how runs are counted, and Make training helps if scenarios are new to you.

Connect

How do you connect Gemini Enterprise Agent Platform to Make?

  1. 01

    Prepare a Google Cloud project

    Sign in with your Google account and open the Google Cloud Platform. Create a project dedicated to Gemini Enterprise Agent Platform, or pick an existing one, so that every call from Make is tied to a project you control.

  2. 02

    Turn on the API and billing

    In that project, enable the Agent Platform API and switch on billing. Both are required by the Make documentation: without them, the connection has nothing to talk to and the modules cannot answer.

  3. 03

    Create the connection in Make

    In your scenario, add any Gemini Enterprise Agent Platform module and click Create a connection. A connection is your Google account linked to Make once; every module of this app reuses it afterwards.

First scenario

Your first scenario with Gemini Enterprise Agent Platform

GoalWhen a new request arrives in another app, Gemini writes a visual brief and Make creates the matching image.

  1. 01

    Create the scenario

    Open the Scenarios page, create a new scenario and click the +. Pick the app where requests arrive, such as your form tool, since this AI app has no trigger of its own.

  2. 02

    Add the chat prompt

    Click the + on the right of the first module, search Gemini Enterprise Agent Platform and choose Create a Chat Prompt (Gemini). Link your account with Create a connection.

  3. 03

    Map the request text

    Fill the prompt with your own instructions and map the text of the request from the previous module. Ask for a short, concrete description of the picture you need.

  4. 04

    Add the image module

    Add Generate an Image after the prompt and map the description Gemini wrote. Each bundle, one item passing from module to module, becomes one image request.

  5. 05

    Test with Run once

    Click Run once, send one test request in your form app and read the bundles each module received. Adjust the wording of the prompt until the image matches what you expect.

  6. 06

    Schedule and switch on

    Set the schedule on the first module, every 15 minutes by default, then switch the scenario on. Each module run counts as one operation on your Make plan.

Modules

What can Gemini Enterprise Agent Platform do in Make?

Gemini Enterprise Agent Platform gives you 7 modules in 3 groups. For each one: what it does for you, when to reach for it, and what to watch out for.

Text Prompts

1 module
Gemini Enterprise Agent Platform1

Create a Chat Prompt (Gemini)

ActionIn the docs only

You get a written answer from Gemini, shaped by your own instructions, ready to map into an email, a document or the next module of the scenario.

When to use it
summarizing a long request, rewriting a product text, or turning raw notes into a brief for the image and video modules.
Watch out
the documentation says this module now accepts image, audio and video inputs, and recommends it over the older media modules.

Images and Videos

5 modules

Note: We've updated the Create a Chat Prompt (Gemini) module to be compatible with image, audio and video inputs. We recommend using that module instead of this one.

Gemini Enterprise Agent Platform2

Generate an Image

ActionIn the docs only

As the name says, this one hands you a fresh picture built from a text description, so a scenario can produce a visual without a designer opening any tool.

When to use it
drafts for a blog cover, a social post or a mood board, right after a prompt module has written a precise description.
Watch out
a vague description gives a vague picture, so test a few prompts with Run once before switching on.
Gemini Enterprise Agent Platform3

Generate a Video

ActionIn the docs only

As its name says, the result is a video created from your description, delivered to the scenario so you can store it or send it for review.

When to use it
a teaser for a product launch or a draft animation for a campaign, when a text brief already exists in another app.
Watch out
on the Free plan a scenario stops after 5 minutes and files are capped at 5 MB, which matters for video.
Gemini Enterprise Agent Platform4

Generate an Image Caption

ActionIn the docs only

Going by its name, you give it a picture and receive a sentence describing what it shows, useful as alt text or as a label in a catalog.

When to use it
a new product photo is uploaded to your storage app and the listing needs a description without anyone writing it by hand.
Watch out
the caption describes, it does not answer questions; for a precise question, the answer module next in this list fits better.
Gemini Enterprise Agent Platform5

Generate an Answer for an Image

ActionIn the docs only

Judging by its name, you ask a specific question about a picture and get a direct answer back, such as whether a receipt shows a total or which error appears in a screenshot.

When to use it
sorting incoming photos or screenshots by what they contain before routing them to the right team.
Watch out
the documentation now points to Create a Chat Prompt (Gemini) for media inputs, so compare both on a test image.
Gemini Enterprise Agent Platform6

Analyze Image/Video (Gemini) (Legacy)

ActionIn the docs only

The older way to have Gemini look at an image or a video and describe it. Keeping it lets scenarios built earlier run as they are.

When to use it
only when you maintain an existing scenario that already relies on it and has no reason to change yet.
Watch out
it is marked Legacy, and the documentation recommends Create a Chat Prompt (Gemini) instead for any new build.

Other

1 module
Gemini Enterprise Agent Platform7

Make an API Call

ActionIn the docs only

With this module you reach any endpoint of the Gemini Enterprise Agent Platform API from your scenario, using the connection you already created.

When to use it
the six ready-made modules do not cover the request you need, and you know which API endpoint does.
Watch out
you write the request yourself here, so keep the API reference of Google Cloud open while you set it up.
Need help

Need help automating Gemini Enterprise Agent Platform with Make?

A person reads every message.

FAQ

Questions about the Gemini Enterprise Agent Platform Make integration

01Is the Gemini Enterprise Agent Platform Make integration free?
Yes on the Make side: it is a standard app, available from the Free plan. That plan allows 2 active scenarios, a minimum of 15 minutes between scheduled runs, 5 minutes of execution per run, files up to 5 MB and 512 MB of data transfer. Paid plans (Core, Pro, Teams and Enterprise) bring the interval down to 1 minute and allow unlimited active scenarios. Google Cloud is separate: billing must be enabled on your project for the connection to work.
02What is needed to connect Gemini Enterprise Agent Platform to Make?
A Google account and an existing Google Cloud project with the Agent Platform API enabled and billing turned on. Once the project is ready, add any module of the app in Make and click Create a connection to link the account. That single connection is then reused by all 7 modules, including Make an API Call. If the connection fails, the usual cause is an API or billing setting that was left off in the project.
03Can Gemini Enterprise Agent Platform trigger a Make scenario in real time?
No, because the app has no trigger module at all. The scenario has to start elsewhere: on a trigger from another app, such as a new form entry or a new file in storage, or on the schedule of the first module, every 15 minutes by default. When that other app offers an instant trigger, meaning it calls Make through a webhook as soon as something happens, the Gemini modules run right after it in the same chain.
04What if a Gemini Enterprise Agent Platform module is missing in Make?
Use Make an API Call. It reaches any endpoint of the app's API with the connection you already have, so a request that none of the six other modules covers is still possible. For image and video work, check Create a Chat Prompt (Gemini) first: the documentation says it now accepts image, audio and video inputs and recommends it over the older media modules. Keep in mind that data received from Google APIs follows the Google API Services User Data Policy.
05Should Gemini Enterprise Agent Platform be automated with Make or n8n?
It depends on the tool your team already uses and knows. Make offers 7 ready modules for this app, a visual editor and a connection shared by every module, which suits a team that wants to start from the ready-made list. The same kind of AI app often has an n8n node too, so check what each tool lists for your exact need before choosing. The best test stays practical: build the same short flow in both and keep the one your team maintains comfortably.
Same platform

Other docs you might need on this stack.

Browse all integrations