Sub-agents and tool output filtering in the 

app, you can now add agents as tools and filter tool outputs.

Previously, agents could use modules, scenarios, and MCP servers as tools, but not other agents. Now, you can add sub-agents as tools for tasks that need their own reasoning and set of tools. 

 The parent agent can delegate tasks to specialized sub-agents, such as reviewers or researchers. 

 Add as many sub-agents to the parent agent as needed to collaborate on complex tasks. 

 A parent agent can have a sub-agent, but a sub-agent can't have another sub-agent.

 Conversation IDs allow the parent agent to continue their conversation with sub-agents across runs. 

To learn how to add agents as tools, see 

Previously, tools that you gave your agent returned the entire output. You can now use tool output filtering to exclude irrelevant fields from outputs and reduce credit usage. 

 Remove fields you don't want the agent to process from tool outputs.

Internal metadata fields from tool outputs are excluded by default. You can include them at any time. 

: Tool output filtering is unavailable in 

To learn how to filter tool outputs, see 

Sub-agents and tool output filtering are now available in the Make AI Agent (New) app

Action required for Stripe users, new Gemini module, and more app updates

Trash for deleting scenarios,  module renaming, AI error explanations, new AI models, and more

Bitbucket modules deprecation, new AI models, and more app updates

Introducing Private spaces

Google Chrome app and browser extension deprecation on August 31, 2026

Functions, standalone module setup, scenario note cloning, and more

New monday.com AI modules, MCP Client update, and more

Content search in Make Grid

Connect your third-party  automation and AI agents

Team edit permission removed from Team Member role

Claude Fable 5 is now available

Claude Sonnet 5 is now available

Databricks app is now available (Enterprise plans)

Introducing User roles visibility

Unified Help search and deprecation of filters

Anthropic Claude model deprecations on June 15, 2026

Make AI Agents (New): MCP tools are now available

Unified canvas navigation

Introducing Make Skills

New module output search, raw data view, undo and redo, and Gemini 3.5 Flash

Nested If-else and Merge is now available

Dynamic labels for HTTP and Sleep modules

New Make Functions app

Deprecated OpenAI audio preview models

Introducing new OpenAI Skills and Skill Versions modules

WhatsApp Business Cloud connections, Bluesky media handling, new xAI and monday.com modules, and more

OpenAI GPT-5.5 is now available in Make

Claude Opus 4.7 now in Make

The Make CLI is now live

Introducing Module Migrator

New version of API endpoint for credential requests, scenario usage tracking, connection filtering, and app updates

Make now a built-in connector on Anthropic Claude

OpenAI GPT-5.4 nano and mini now available in Make

Make Grid workspace navigation and interaction updates

Introducing Scenario recovery

Scenario Builder improvements, new app, and AI model updates

OpenAI GPT-5.4 and GPT-5.3 models now available in Make

OpenAI model deprecations on March 26, 2026

New feature: If-else and Merge

Credential requests reauthorization, 2FA enforcement logs

Gemini 3.1 Pro Preview model now available in Make

New MMS options, app updates

Deprecated OpenAI model automatically replaced

Filter copying, smarter app search, and scenario sorting

Introducing two-factor authentication enforcement

Meet the new Make AI Agents app

monday.com app v1 to v2 transition by May 1, 2026

Introducing MCP toolboxes

Introducing Credential requests

Claude Opus 4.6 now available in Make

New payment methods for greater flexibility

Pipedrive API v1 to v2 transition by July 31, 2026

Scenario history and run replay improvements, app updates

2026

A safety feature that saves unfinished scenario runs when errors occur, preventing data loss. Stored in the Incomplete Executions tab, you can retry automatically, resolve manually, or delete them. Disabled by default, enable it in Scenario settings.

Incomplete_executions

incomplete_executions

Error handlers act as a safety net that catches unexpected failures to prevent your scenarios from failing. They allow you to define exactly how the system should react, such as by retrying the task, ignoring the mistake, or rolling back changes.

error_handler

The Rollback error handler stops a scenario and reverts changes made by modules that support transactions to ensure data remains consistent when an error occurs.

Rollback

An automated workflow within the Make platform. You build it by connecting modules together, and it runs based on a trigger you set up.

scenario

a list or sequence of characters (like letters, numbers, and symbols) used to represent text in a computer programming.

string

An operation is a single module run to process data or check for new data. 

Operations

Credits (formerly operations) are the currency for running scenarios.

Credits

A route is a path that data can flow through in a scenario, visualized as the dotted lines between modules.

Route

scenario_plural_lowercase

scenario_singular_lowercase

Scenario_plural

Scenario_singular

product_name

Help Center

What is Make?

What's an API?

What's a scenario and which type should you use?

Learn the basics

Step 1. Plan your scenario

Step 2. Get your apps ready

Step 3. Add your first app

Step 4. Create a connection

Step 5. Set up the trigger

Step 6. Test the module

Step 7. Add another module

Step 8. Map data

Step 9. Test your scenario

Step 10. Schedule your scenario

Create your first scenario

Step 1. Get your app ready

Step 2. Add a router

Step 3. Set up another module

Step 4. Add a filter

Step 5. Test your scenario

Step 6. Add an aggregator

Step 7. Test the final scenario

Expand your scenario

Get started

Credits & operations

Connect an application

Schedule a scenario

Clone a scenario

Delete a scenario

Active and inactive scenarios

Scenario execution flow

Scenario history

Scenario blueprints

Scenario templates

Scenario sharing

Scenarios & connections

Introduction to Make apps

Types of modules

Module settings

Update legacy modules with new modules

Webhooks

Select the first bundle to process

Apps & modules

Item data types

Type coercion

Mapping

Filtering

Mapping arrays

Working with files

Data & mapping

Aggregator

Iterator

Router

Tools

Keyboard shortcuts

Resources

Canvas interaction model

Key concepts

Scenario settings

Scenario notes

Scenario inputs and outputs

Subscenarios

Create and manage scenario templates

Custom scenario properties

Variables

Incomplete executions

Scenario execution, cycles, and phases

Restore and recover scenario

Undo and redo scenario changes

Scenario run replay

Scenarios

Call Google APIs with OAuth 2.0 HTTP request

Connect to any web service using OAuth 2.0

Connect to Google services using a custom OAuth client

Replace connections across multiple modules

Credential requests

Dynamic connections

On-premise agent

Devices

Keys and certificates

Allow connections to and from Make IP addresses

Connections

If-else and Merge

Flow control

Converger

Text parser

Use functions

General functions

Math functions

Math variables

Text and binary functions

Date and time functions

Tokens for date/time parsing

Tokens for date/time formatting

Array functions

Custom functions

Functions

Methods of securing data

AES (Advanced Encryption Standard)

PGP (Pretty Good Privacy)

Digital signature

Hash functions

Securing data with Make

Data stores

Data structures

Make DevTool

Developers

Explore more

Introduction to Make AI Agent (New)

Create your first AI agent

Make AI Agent (New)