Resources · Make integration

Agent.AI Make integrationAutomate Agent.AI with Make.

Can an Agent.AI agent run inside your other tools without you opening Agent.AI? The Agent.AI Make integration gives you 3 modules: 2 actions and 1 search. This guide shows how to link your account with an API key, then build and test a first scenario.

Try the Agent.AI integration on MakeSee the 3 modules

Verified Trustpilot reviews · AI, automation & growth agency

What you can automate

What can the Agent.AI Make integration do for you?

The Agent.AI Make integration lets a Make scenario call an Agent.AI agent and pass the result to your other apps. A scenario is the automation you build in Make, a chain of modules, and a module is one brick of that chain. Agent.AI brings three of them, and none is a trigger, so something else starts the flow.

Put an agent behind a form or a sheet. A new row or a new submission in another app starts the scenario, and Call an Agent sends that content to the agent you pick. Whatever comes back can be mapped into the next module, for example an email or a row update.

Keep an inventory of your agents. Search Agents returns a list of agents, one bundle per agent (a bundle is one item passed from module to module). Send that list to a spreadsheet and your team sees what exists before anyone builds a duplicate.

Reach what the two actions skip. Make an API Call uses the same connection to call any endpoint of the Agent.AI API, handy when a need falls outside the listed modules.

What Make does not give you here: a trigger. Agent.AI cannot start a scenario on its own, so you run it on a schedule or from another app. The documentation lists no numeric limits either. Before you scale up, the Make pricing page explains how operations are counted, and the n8n vs Make comparison helps if you are still choosing a platform. For a guided start, the Make training covers scenario building from scratch.

Connect

How do you connect your Agent.AI account to Make?

  1. 01

    Copy your API key in Agent.AI

    Log in to Agent.AI, click your profile icon in the top-right corner, then Integrations. Open the API tab and copy the key shown there. Keep it somewhere safe, since Make will ask for it in a moment.

  2. 02

    Open the connection window in Make

    In your scenario, add any Agent.AI module and click Create a connection. A connection is your Agent.AI account linked to Make once, and every Agent.AI module reuses it. The Connection name field is optional.

  3. 03

    Paste the key and save

    Paste your key into Your Agent.AI API Key and click Save. If Make asks you to authenticate your account and confirm access, accept it. The module can now talk to Agent.AI.

First scenario

Build your first scenario with Agent.AI

GoalWhen the scenario runs, Search Agents lists Agent.AI agents and Call an Agent runs for each agent in that list.

  1. 01

    Create the scenario

    Go to the Scenarios page, create a new scenario and click the big + to place the first module. Type Agent.AI in the search box and pick Search Agents.

  2. 02

    Link your account

    Click Create a connection, paste your API key and save. Then fill the module fields; once the connection exists, Make can show you what it reads from Agent.AI.

  3. 03

    Add Call an Agent

    Click the + on the right of Search Agents and choose Call an Agent. Map data from the first module into its fields. Search Agents sends one bundle per agent, so Call an Agent runs once for each of them.

  4. 04

    Test with Run once

    Click Run once. Make executes the scenario one time, and you can open each module to read the bundles it received. Check the agent answered before going further.

  5. 05

    Schedule and switch on

    Open the clock on the first module. A new scenario runs every 15 minutes by default; change it if needed, then switch the scenario on. Each module run counts as one operation on your plan.

Modules

What each Agent.AI module does

Agent.AI gives you 3 modules in 2 groups. For each one: what it does for you, when to reach for it, and what to watch out for.

Actions

2 modules
Agent.AI1

Call an Agent

Action

In Make“Calls an AI Agent.”

You get an Agent.AI agent working inside your scenario: this module calls the agent and hands its reply to the modules that follow, so a text, a lead or a request from another app gets processed without a copy and paste.

When to use it
a new form entry should reach an agent and the answer should land in your CRM or inbox.
Watch out
every run counts as one operation, and after a search it runs once per bundle, so feed it only the items that need the agent.
Agent.AI2

Make an API Call

Action

In Make“Performs an arbitrary authorized API call.”

This gives you access to any endpoint of the Agent.AI API, with the connection you already created, so a need that the other two modules do not cover still stays inside Make instead of a separate script.

When to use it
Call an Agent and Search Agents stop short of what your process requires.
Watch out
you write the request yourself, so keep the Agent.AI API documentation open while you write it.

Searches

1 module
Agent.AI3

Search Agents

Search

In Make“Returns a list of agents.”

You get a list of agents, returned as separate bundles, one per agent, which you can route to a sheet, a filter or the next action. It turns what sits in Agent.AI into data your scenario can read.

When to use it
before Call an Agent, to pick the right agent from the list rather than typing it by hand.
Watch out
a search can return zero, one or many bundles, and every module after it runs once per bundle.
Need help

Need help automating Agent.AI with Make?

A person reads every message.

FAQ

Agent.AI and Make: common questions

01Is the Agent.AI Make integration free?
Yes, on the Make side. Agent.AI is a standard app, available from the Free plan, like the 3,000+ standard apps on every plan. The Free plan allows 2 active scenarios, a minimum interval 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 drop the interval to 1 minute, remove the cap on active scenarios and allow 40 minutes of execution. Your Agent.AI account itself is a separate matter, and this page does not cover its pricing.
02What do you need to connect Agent.AI to Make?
You need an Agent.AI account and its API key. In Agent.AI, click your profile icon in the top-right corner, open Integrations, then the API tab, and copy the key. In Make, add an Agent.AI module, click Create a connection, paste the key into the Your Agent.AI API Key field and click Save. If Make asks you to authenticate and confirm access, accept. The same connection then serves all three modules, including Make an API Call, so you only do this once per account.
03Can an Agent.AI event start a Make scenario in real time?
No. Agent.AI has no trigger module in Make, neither scheduled nor instant, so nothing in Agent.AI can start a scenario by itself. You have two ways to start one anyway. Put a trigger from another app first, such as a new form entry or a new row, and follow it with Call an Agent. Or open with Search Agents and let the scenario schedule decide when it runs: a new scenario checks every 15 minutes by default, and the Free plan does not go below that interval.
04What if the Agent.AI module you need is missing in Make?
Use Make an API Call. It reaches any endpoint of the Agent.AI API with the connection you already have, which covers what Call an Agent and Search Agents leave out. You build the request yourself, so keep the Agent.AI API documentation at hand. The Make documentation for this app gives no numeric limits, so there is no documented quota to plan around on the Make side. If an error persists, test the scenario with Run once and read the bundle each module received before changing anything.
05Make or n8n for Agent.AI automations?
It depends on what you already use. In Make, Agent.AI comes with three ready modules plus Make an API Call, and the connection takes an API key and a click on Save, which suits a team that builds visually. This page cannot confirm whether n8n ships a dedicated Agent.AI node, so check that before you decide. If your other automations already live on one platform, keeping Agent.AI there is usually the simpler choice. The comparison page linked above lays out the criteria side by side.
Same platform

Other docs you might need on this stack.

Browse all integrations