Step 2. Create the AI agent's tools

3 min

This page reflects a previous version of Make AI Agents. For the latest information, see Make AI Agent (New).

AI agents in Make need tools to do their job – these tools are modules, scenarios and MCP tools. Agents use information provided by you to reason about how and when to use these tools.

To inform the AI agent's context, Make sends the following information to the AI service provider:

System prompt

The name and description of each tool

The name and description of inputs or outputs of the scenario used as a tool

In addition to providing context, all scenarios used as tools for AI agents must be active and either scheduled on demand or triggered by a Custom webhook.

In the next sections, we will create a tool for our agent to list our shop inventory and another to order more stock if we're low.

The aim of the following sections is to showcase the AI agent's reasoning. The example scenarios provided have been simplified to streamline their setup.

Tool 1: Scenario to list shop inventory

We will provide our agent with a scenario to list our shop inventory. Since we want to send data from the scenario to the agent, we have to use scenario outputs and the Scenarios > Return output module.

To create the scenario:

Click the Create a new scenario button in your organization dashboard or in the list of scenarios.

If you don't have testing data ready, set up your shop data:

Add the Data store > Search record module to your scenario.

In the Data store field, select Add to create a new data store.

In the Data store name field, fill in the name for your inventory data storage.

In the Data structure box, click Add to define a structure for your data store.

Click Save to confirm the data structure and Save to create the data store.

Go to the list of data store and open the new data store.

Click the Add button to add data to your data store:

Update the name of the scenario. The AI agent uses the scenario name to decide if it should run the scenario. Fill in: "List shop inventory".

Add the Tools > Text aggregator module

In the Source module field, keep the data store module.

Enable the dvanced settings toggle at the bottom of the module settings.

In the Row separator field, select New row.

In the Text field, map the name and quantity fields from your data store:

Add the Scenarios > Return output module.

Click Add scenario outputs to set scenario outputs for the return data module.

In the Scenario outputs tab, define the scenario output structure and fill in the description of each item in the output:

In the module settings, map the text variable to the inventory field.

Confirm module settings with Save.

Set scenario scheduling:

Set the scenario scheduling to On demand. The agent will run the scenario for you when needed.

Confirm the scenario scheduling with Save.

Activate the scenario.

Save your scenario.

Add scenario description for the agent:

Go to the scenario Diagram tab.

Click Options > Edit description.

Add description to the scenario. The AI agent uses the scenario name and description to decide if it should run the scenario. Fill in: "Lists the shop inventory."

Click Save.

You have created the scenario for your agent to list the shop inventory. We will make the scenario available to your agent in the following sections.

Tool 2: Scenario to order more stock

We will provide the agent with another tool: a scenario to order more items for our shop inventory. The scenario will receive order information from the agent with scenario inputs.

For our testing purposes, the scenario will just send messages to a selected chat.

To create the scenario:

Click the Create a new scenario button in your organization dashboard or in the list of scenarios.

In Scenario inputs and outputs in the Scenario inputs tab, set the scenario inputs structure and description:

Add the Slack > Create a message module.

Set up the Create a message module:

In the Connection selection box, select your connection. If you don't have a connection, click the Add button to create it.

Select the channel where you want to receive the messages about new orders created by the agent.

In the module settings, use the scenario input in the Text field. For example:

Update the name of the scenario. The AI agent uses the scenario name to decide if it should run the scenario. Fill in: "Create buy stock order."

Set scenario scheduling:

Set the scenario scheduling to On demand. The agent will run the scenario for you when needed.

Confirm the scenario scheduling with Save.

Activate the scenario.

Save your scenario.

Add scenario description for the agent:

Go to the scenario Diagram tab.

Click Options > Edit description.

Add description to the scenario. The AI agent uses the scenario name and description to decide if it should run the scenario. Fill in: "Creates orders to refill the shop inventory."

Click Save.

You have created the scenario for your agent to create orders to refill the shop inventory. We will make the scenario available to your agent in following sections.