The 0.1% Expert Guide · Updated June 2026

Master
Make.com

Everything you need to go from zero to automating AI-powered workflows, building agentic systems, and running your entire business on autopilot — no code required.

Start Free on Make.com → Read the Guide ↓

📋 What's in This Guide

The Visual AI Automation Platform

Make (formerly Integromat) is a no-code/low-code automation platform that lets you visually connect apps, automate workflows, and build AI-powered systems — without writing a line of code. Think of it as the command center for your entire digital operation.

🟣 The One-Sentence Pitch

Make lets you visually build, scale, and automate AI and agentic workflows by connecting any app, data source, or AI model — through an intuitive drag-and-drop canvas.

🎨

Visual-First Builder

Design workflows on a canvas using drag-and-drop modules. See data flowing in real time. No code needed for most tasks.

🔌

3,000+ App Integrations

Connect Gmail, Slack, HubSpot, Notion, OpenAI, Airtable, Google Sheets, Stripe, and thousands more out of the box.

🤖

AI & Agentic Automation

Embed AI models and agents directly in your workflows. Make handles judgment-based, adaptive tasks that traditional automation can't.

Real-Time Execution

Watch your scenarios run live. Monitor every step, inspect data at each node, and debug instantly on the canvas.

🏢

Enterprise-Grade Security

SOC 2 Type II, GDPR compliant, SSO, encryption at rest and in transit, audit logs, and on-prem agent support.

📐

Scales With You

Start free, scale to millions of operations. From a single workflow to an AI automation system running your whole business.


Make vs. Competitors

Feature Make Zapier n8n
Visual Canvas Builder✅ Full visual canvas with live data flow⚠️ Linear, list-based✅ Node-based
AI Agents✅ Native AI Agents on all plans⚠️ Limited✅ Supported
Pricing ModelCredit-based (per operation)Task-basedSelf-host free
Free Plan1,000 credits/mo, no time limit100 tasks/moSelf-host only
No-Code RequirementZero code neededZero codeSome setup
Real-Time Monitoring✅ Live on canvas⚠️ Logs only✅ Supported
MCP Server✅ Native Make MCP⚠️ Via plugins

The Make Vocabulary

Before you build, understand these building blocks. Everything in Make is built on top of these concepts.

🔵 Scenario

Foundation

A scenario is your automated workflow. It defines how different apps communicate and work together. A scenario triggers when it receives data, transforms it, and sends it to another app.

Example: New Typeform submission → OpenAI generates a reply → Gmail sends it automatically.

🟢 Module

Building Block

Modules are the individual nodes in your scenario. Each module performs one action — triggering, searching, creating, updating, or transforming data. Each module execution = 1 credit.

Types: Trigger, Action, Search, Iterator, Aggregator, Router, Tools.

⚡ Trigger

Starter

Every scenario starts with a trigger — the event that kicks off the automation. Can be a webhook (instant), a schedule (every X minutes), or polling (checks for new data at intervals).

Examples: New email, form submission, scheduled time, webhook from your app.

🔀 Router

Logic

Routers split a scenario into multiple parallel paths based on conditions. One path might email VIP customers, another handles standard customers. No extra credits charged for the router itself.

Note: Filters inside routers let you add conditions like "only proceed if price > $100."

🗃️ Data Store

Storage

Built-in database for your scenarios. Store data between runs, track state, deduplicate records, and build persistent memory into your automations without an external database.

Limit: 1 MB per data store; up to 1,000 data stores per organization.

🔗 Connection

Authentication

Connections are the authorized links between Make and your apps. You authenticate once (OAuth, API key, etc.) and reuse the connection across unlimited scenarios.

Tip: Share connections across team members for centralized credential management.

🪝 Webhook

Instant Trigger

A unique URL that triggers your scenario instantly when called. Used for real-time automation — any app that can send an HTTP request can trigger your Make workflow.

🔗 Subscenario

Advanced

Chain scenarios together. One scenario can call another, enabling modular, reusable automation. Build once, use across multiple parent workflows — like functions in programming.

💡

How Credits Work

Each module action in your scenario consumes 1 credit. Reading a Google Sheet row = 1 credit. Sending a Gmail = 1 credit. An OpenAI call = 1 credit. Error handler modules (Rollback, Break, Resume, Commit, Ignore) and Router modules do not consume credits. Plan accordingly — a scenario with 10 modules that runs 100 times/day uses ~1,000 credits/day.

How to Build Your First Automation

Building a scenario in Make is faster than you think. Here's the complete process from account creation to your first running automation.

🏗️ Anatomy of a Scenario: Example


📧
Gmail
Watch Emails
🤖
OpenAI
Analyze Sentiment
🔀
Router
Positive/Negative
📊
Airtable
Add Record
💬
Slack
Send Alert

This 5-module scenario watches Gmail, analyzes sentiment with AI, routes to Airtable logging, and pings Slack for negative emails — uses ~5 credits per email.


Key Scenario Settings to Know

🔁 Scheduling

Free plan: run every 15 minutes minimum. Paid plans: run every 1 minute, or at an exact time. Webhook-triggered scenarios run instantly when called, consuming no polling time.

⚠️ Error Handling

Add error handlers (Break, Retry, Ignore, Resume, Rollback, Commit) to specific modules. Set email alerts when scenarios fail. Incomplete executions are saved automatically for retry.

📦 Data Bundles

Make processes data in "bundles" — each record from a trigger becomes a bundle flowing through your scenario. The Iterator module splits arrays into individual bundles; Aggregator collects them back.

🔢 Variable Mapping

Every module output is mappable as a variable in downstream modules. Use the mapping panel to reference data like {{1.email}} — the output of module 1's email field.

Make + AI: Intelligent Workflows

Make is built AI-first. Every plan includes access to 350+ AI integrations, the Make AI Toolkit, and native AI features — no separate subscription needed.

🧠

Make AI Toolkit

Built-in AI tools using Make's own AI Provider — available on all plans. No external API key required to get started. Includes text processing, content generation, and classification tools.

All Plans
🔍

AI Content Extractor

Extract structured text and metadata from PDFs, docs, images, and web pages directly within your scenario. Turn unstructured content into clean, actionable data.

All Plans
🌐

AI Web Search

Bring live web data into your automations with built-in AI search and structured outputs. Research topics, verify facts, or gather competitive intelligence — automatically.

Beta

How to Set Up an AI Automation

Follow these steps to add AI to any workflow:

  • Choose Your AI App

    In your scenario, click + to add a module. Search for OpenAI, Anthropic Claude, Google Gemini, Mistral, or the built-in Make AI Toolkit. Each has pre-built action modules for common AI tasks.

  • Connect Your API Key (or Use Make's AI Provider)

    For external AI apps (OpenAI, Claude, etc.), add your API key as a connection. Alternatively, use Make's built-in AI Provider — no API key needed, credits deducted from your plan at a slightly higher rate per AI call.

  • Map Your Prompt & Variables

    In the AI module's "Messages" or "Prompt" field, type your prompt and insert mapped variables from earlier modules. Example: "Summarize this email: {{1.text.content}}" — the output from your Gmail trigger flows directly into the AI prompt.

  • Use the AI Output Downstream

    The AI module's response becomes a mappable variable for all following modules. The generated text, structured JSON, or classification label can be used in any app — create a Google Doc, send a Slack message, update a CRM, etc.


Popular AI Automation Patterns

📝 Content Generation Pipeline

Trigger: New product in Airtable → OpenAI writes 5 social captions + blog intro → Store to Google Sheets → Post to Buffer for scheduling.

📊 Sentiment Analysis

Trigger: New customer review → Claude analyzes tone & category → Route to different Slack channels (#praise vs #issues) → Update NPS dashboard.

📧 Smart Email Triage

Trigger: Gmail new email → AI classifies intent (sales lead, support, spam) → Routes to appropriate team member via Slack + creates task in Asana.

🖼️ AI Image Generation

Trigger: Typeform content brief → GPT-4 writes prompt → DALL-E 3 generates image → Upload to Dropbox → Share link in Slack thread.

📄 Document Intelligence

Trigger: PDF uploaded to Google Drive → AI Content Extractor pulls structured data → Parse fields → Create CRM record in HubSpot with extracted info.

🌐 AI-Powered Research

Trigger: Scheduled daily → AI Web Search for competitor news → Summarize with Claude → Add to Notion research database → Email digest to team.

Build Transparent AI Agents

Make AI Agents are the next evolution beyond traditional automation. While a standard scenario follows fixed logic, an AI Agent reasons, decides what to do next, and takes action across 3,000+ apps.

🤖 Agent vs. Scenario: The Core Difference


Standard Scenario

Deterministic — it always follows the same path. If X then Y. Great for predictable, repeatable processes. You define every step in advance.

Make AI Agent

Non-deterministic — the AI decides what action to take based on context. It can reason, handle exceptions, and choose from available tools dynamically.

Rule of thumb: "If it just needs doing, use automation. If it needs thinking, use Make AI Agents."

How to Build an AI Agent in Make

  • Open the AI Agent Builder

    In your Make dashboard, go to AI Agents (left sidebar) → Create new agent. Or add an "AI Agent" module inside an existing scenario on the canvas.

  • Define the Agent's Role & Instructions

    Write a system prompt that defines what your agent does: its persona, goals, constraints, and tone. Be specific: "You are a customer support agent for [Company]. Always check the knowledge base before answering. Escalate to human if the issue involves billing."

  • Choose Your LLM

    Select from Make's AI Provider (all plans), or connect your own API key for OpenAI GPT-4o, Anthropic Claude, Google Gemini, Mistral, or others. Higher-capability models cost more credits per run.

  • Attach Tools (Scenarios as Functions)

    Tools are Make scenarios that the Agent can call as needed. Example: "Search CRM" scenario, "Create Ticket" scenario, "Look Up Knowledge Base" scenario. The Agent decides which tool to use and when, based on the conversation context.

  • Connect Inputs & Memory

    Define how the Agent receives input — webhook, chat interface, email trigger, or Slack message. Add memory modules to give the Agent context from previous conversations using a Data Store or external database.

  • Test with the Reasoning Panel

    Run the agent and open the Reasoning Panel — you see every decision the agent makes, which tool it chose and why, step by step. This transparent "thinking" is Make's key differentiator for building trustworthy agents.

  • Add Human-in-the-Loop Checkpoints

    For high-stakes actions, add approval steps: the agent pauses and sends a Slack message asking "Shall I proceed?" Your team confirms or redirects before the agent continues.


Ready-Made Agent Examples (Agent Library)

Make's Library of Agents has pre-built agents you can deploy and customize instantly:

📋

AI Recruiting Agent

Fetches resumes, evaluates candidates against job criteria, ranks applicants, and notifies hiring managers — automated from inbox to shortlist.

💬

Customer Support Chatbot Agent

Handles complex queries, searches a knowledge base, creates tickets, escalates to humans when needed — 24/7 without a support team member present.

📊

Expense Audit Agent

Reviews submitted expense reports, checks policy compliance, flags exceptions, and routes for approval — reducing audit time from hours to seconds.

🌾

Invoicing Agent

Based on Make's real customer case study: reduced farmers' invoicing time from 15 minutes to 20 seconds — reading inputs, generating invoices, and sending via email.

The Next Tier: Agentic Workflows

Agentic automation is where traditional automation ends and intelligent, adaptive systems begin. It's AI that doesn't just execute — it reasons, adapts, and responds to real-world complexity.

🔄

Real-Time Adaptability

Agentic workflows respond to new inputs and changing conditions dynamically. No need to pre-define every possible edge case — the AI adapts in the moment.

📈

Scalability Without Replanning

Traditional automation breaks when you add new products, markets, or edge cases. Agentic workflows grow alongside your business without constant rebuilding.

🎯

Handles Unstructured Data

Unlike rule-based automation, agentic systems can interpret free-form text, context-heavy emails, PDFs, and natural language — without structured inputs.

🔐

Security Built In

Every AI-driven workflow is encrypted, logged with full execution history (including reasoning steps), and protected with third-party audits and DDoS protection.

Agentic vs. Traditional vs. AI-Assisted: The Spectrum

Traditional automation: Structured, deterministic. If A happens, do B. No interpretation. Example: Copy Typeform response to Google Sheet.

AI-Assisted automation: Fixed workflow + AI for one step. Example: Send email body to GPT to generate a reply, then send that reply.

Agentic automation: The AI decides the entire path. It reads context, picks tools, takes actions, handles exceptions, and loops until the goal is achieved — adapting at every step.

Make MCP Server

Make MCP (Model Context Protocol) Server lets your AI tools outside Make — like Claude Desktop, Cursor, custom chatbots — connect to and trigger your Make scenarios directly. It's a bridge that turns Make into a backend for any AI interface.

Example: You're chatting with Claude and say "Create a new lead in my CRM from this email." Claude uses Make's MCP Server to call your "Create HubSpot Lead" scenario directly — no copy-paste, no switching apps. Available on all plans.

400+ AI Apps You Can Connect

Make has the richest AI integration library of any automation platform. Every major model provider, voice AI tool, image generator, and AI infrastructure service is available as a native module.

🧠 Large Language Models

OpenAI (GPT-4o, Sora, Whisper, DALL-E)
Anthropic Claude
Google Vertex AI / Gemini
Azure OpenAI
Mistral AI
DeepSeek AI
Perplexity AI
Hugging Face

🎙️ Voice & Audio AI

ElevenLabs (Voice Cloning & TTS)
OpenAI Whisper (Transcription)
AssemblyAI
Deepgram
Rev.ai

🎬 Video AI

Synthesia (AI Video Avatars)
D-ID
HeyGen
RunwayML

🖼️ Image AI

DALL-E 3 (via OpenAI)
Stable Diffusion
Ideogram
Midjourney (via API)
Adobe Firefly

🔧 AI Infrastructure

Pinecone (Vector DB)
Weaviate
LangChain
Eden AI
Cohere
Replicate
💡
Pro Tip: Browse the full AI category at make.com/en/integrations/category/ai. New AI apps are added weekly — check the "What's New" page to stay current.

What Make Can Automate Across Your Business

Make has pre-built solution paths for every department. Here's what each team can automate — with concrete examples.

📣 Marketing Automation

  • Auto-post content across social platforms (Buffer, Later, Instagram, LinkedIn)
  • Score and nurture leads from ads → CRM → email sequences
  • Generate SEO-optimized blog posts from keyword inputs
  • Sync contacts between ActiveCampaign, HubSpot, Mailchimp
  • Monitor brand mentions and trigger engagement workflows

💼 Sales Automation

  • Qualify leads via AI + route to correct sales rep in CRM
  • Sync Salesforce, HubSpot, Pipedrive with one source of truth
  • Auto-generate proposal docs from CRM data in Google Docs
  • Send personalized outreach sequences triggered by behavior
  • Real-time Slack alerts when a deal changes stage

⚙️ Operations

  • Sync project data across Asana, Jira, Monday.com, Notion
  • Automate approval workflows and status updates
  • On/offboard employees across 10+ tools in one click
  • Build custom dashboards pulling from multiple data sources
  • Incident response automation — detect, alert, log, resolve

🛎️ Customer Experience

  • AI chatbot that resolves 60%+ of support queries autonomously
  • Auto-create Zendesk/Intercom tickets from emails or forms
  • NPS survey triggers → analyze sentiment → route response
  • Customer onboarding sequences across email + product + Slack
  • Smart escalation routing based on issue type and urgency

💰 Finance Automation

  • Quote-to-cash: proposal → e-sign → invoice → payment tracking
  • Expense report processing with AI policy compliance checks
  • Sync Stripe, QuickBooks, Xero, and NetSuite automatically
  • Overdue invoice reminders sent to the right contacts
  • Financial report generation into Google Sheets/Notion

👥 HR & People Ops

  • AI recruiting agent: screen resumes, rank candidates, schedule interviews
  • New hire onboarding: create accounts, send welcome docs, assign training
  • Offboarding: revoke access across all tools, transfer files, final payroll
  • Performance review data collection and aggregation
  • Time-off requests → approval → calendar → payroll sync

📱 Social Media & Content Creation (Popular Use Case)

Make specifically highlights Social Media Posting and Content Creation as two of its most popular automations. Connect your content creation tools to auto-publish across platforms, repurpose long-form content, and scale your online presence without manual copy-paste.

Featured example from Make's how-to guides: "Repurpose TikTok Videos into LinkedIn Posts" — one of their most popular tutorials.

Plans That Grow With You

Make pricing is credit-based — each module action consumes 1 credit. No time limit on the free plan. All plans include AI features.

FREE
$0/mo
1,000 credits/mo
  • 2 active scenarios max
  • 15-min minimum run interval
  • 5 MB max file size
  • 5-min max execution time
  • 512 MB data transfer
  • 90-day expert onboarding
  • AI Toolkit included
  • 3,000+ apps
  • 7-day execution logs
CORE
$12/mo
10k credits/mo (base)
  • Unlimited active scenarios
  • 1-min minimum interval
  • 100 MB max file size
  • 40-min max execution
  • 5 GB data transfer per 10k credits
  • Make API access (60 calls/min)
  • Technical support
  • 30-day execution logs
TEAMS
$38/mo
10k credits/mo (base)
  • Team roles & permissions
  • Create & share templates
  • Priority execution
  • 500 MB max file size
  • API: 240 calls/min
  • All Pro features
ENTERPRISE
Custom
Custom volume
  • 24/7 senior specialist support
  • SSO & domain claim
  • Audit logs & analytics
  • Custom functions (JS)
  • Enterprise app integrations
  • Overage protection
  • 1,000 MB max file size
  • API: 1,000 calls/min
  • On-prem agent
  • 60-day execution logs
💰
Save 15%+ with annual billing. Unused credits expire monthly (monthly plan) or annually (annual plan). If you run out, you can buy extra credits in 1,000 or 10,000 credit bundles. Scenarios pause when credits run out, but incoming webhooks queue up and process when you top up.
🎯
Which plan to start on? Start Free to build your first 2 scenarios and get the feel. Upgrade to Core ($12/mo) when you need unlimited active scenarios and minute-level scheduling. Jump to Pro when you need full-text log search and priority execution. Teams when you add collaborators.

Credits Calculator: Estimate Your Usage

Scenario Type Modules Runs/Day Credits/Day Credits/Month
Simple 2-app sync348×144~4,300
Email → AI → CRM520×100~3,000
Content pipeline (social)840~1,200
Lead qualification workflow1030×300~9,000
AI agent (10 tool calls avg)1510×150~4,500

Make for Content Creators

If you're a creator, Make is one of the highest-leverage tools you can learn. These workflows save 10+ hours per week and let you publish more, better, with less manual effort.

📹

Video-to-Multi-Platform Repurposing

Turn one long video into 5+ pieces of content automatically

01 New video uploaded to Google Drive or YouTube
02 Whisper API transcribes the audio
03 GPT-4 generates: 5 tweets, 1 LinkedIn post, 3 Instagram captions, 1 blog intro, 10 short-form hooks
04 All content saved to Notion content database
05 Slack notification: "Content ready for review" with Notion link
📝

AI Blog → Social Content Pipeline

From idea to published across all channels automatically

01 Fill Tally or Typeform with topic + keywords + tone
02 Claude writes full blog post (SEO-optimized, with H2s)
03 DALL-E generates featured image based on title
04 Post published to WordPress/Ghost via API
05 GPT extracts 10 social quotes → Buffer scheduled for 2 weeks
🎵

TikTok / Reels Auto-Repurpose

Per Make's official how-to guide: TikToks → LinkedIn posts

01 Monitor TikTok RSS or webhook for new videos
02 Extract video caption and transcription
03 GPT rewrites for LinkedIn's professional tone
04 Post scheduled to LinkedIn via Buffer or direct API
05 Cross-post versions to Twitter, Instagram, newsletter
📧

Newsletter Automation System

Curate, write, and send — fully automated

01 Scheduled weekly trigger (Monday 8am)
02 AI Web Search pulls top 10 stories in your niche
03 Claude summarizes + adds your editorial voice per story
04 Newsletter draft created in ConvertKit or Beehiiv
05 Slack notification for 1-click human review before send
📊

Content Performance Intelligence

Know what's working without manual analytics check

01 Scheduled daily pull from YouTube Analytics + Instagram API
02 Data normalized and stored in Airtable/Google Sheets
03 GPT identifies top 3 performers + why (based on metadata)
04 Weekly insight report emailed every Sunday evening

Best Apps for Creators on Make

Content Creation

OpenAI / ChatGPT
Anthropic Claude
ElevenLabs
DALL-E
Whisper

Publishing & Scheduling

Buffer
Later
Hootsuite
WordPress
Ghost

Email & Community

ConvertKit
Beehiiv
Mailchimp
Substack
Discord

Organization & Storage

Notion
Airtable
Google Drive
Dropbox
Google Sheets

Forms & Intake

Typeform
Tally
JotForm
Google Forms

Notifications & Collab

Slack
Telegram
Gmail
Twilio SMS

Make Academy, Help Center & Community

Make has one of the best free learning ecosystems of any automation platform. Here's where to go for every learning need.

🎓

Make Academy

Free structured eLearning at academy.make.com. Courses from beginner to advanced covering scenarios, AI, agents, and enterprise use cases. Self-paced with certification options.

Best for: Structured learners who want official certification.

📚

Help Center

Full documentation at help.make.com. Covers every module, app, feature, and billing question. Searchable, always updated. Start here when stuck.

Best for: "How do I do X exactly?" reference questions.

🗺️

How-to Guides

191+ step-by-step tutorials at make.com/en/how-to-guides. Practical, real-world use cases with screenshots. Updated weekly — new guides include LLM integrations and AI agent workflows.

Best for: "I want to build X" — find a near-exact template.

💬

Make Community

Active forum at community.make.com. 350,000+ users sharing templates, solving bugs, and posting workflows. The fastest way to get unstuck when you have a specific problem.

Best for: Debugging, edge cases, finding creative solutions.

📋

Templates Library

Hundreds of pre-built scenarios at make.com/en/templates. One-click install to your account. Filter by app, use case, or department. Best place to get started fast.

Best for: Getting your first automation live in under 5 minutes.

🎙️

Webinars

Live expert-led sessions at make.com/en/webinars. Q&A with Make experts, live scenario building, and product deep-dives. Recordings available after.

Best for: Watching an expert build in real time.

📚 Recommended Learning Path for Beginners

  • Week 1: Make Academy Fundamentals

    Complete the "Make Foundations" course at academy.make.com. Takes ~3 hours. You'll understand scenarios, modules, connections, and the canvas.

  • Week 1: Build Your First 3 Scenarios from Templates

    Go to Templates, install a Gmail→Slack, a Google Sheets sync, and a form-to-email scenario. Run them, inspect the data, see how it works.

  • Week 2: Build One AI Scenario from Scratch

    Follow the "How to create AI chatbots with Make" how-to guide. Build it without a template. This is where it clicks.

  • Week 2-3: Build Your First AI Agent

    Follow "How to build AI agents with Make" guide. Deploy one from the Agent Library, customize the system prompt and tools. Test with the Reasoning Panel.

  • Ongoing: Community + How-to Guides

    Bookmark community.make.com. Every time you're stuck for more than 10 minutes, search the community first. Subscribe to the Make blog for weekly automation inspiration.

Everything You Need, One Place



⚡ Top 10 Expert Tips

1️⃣
Use Webhooks whenever possible. Polling consumes credits even when nothing changed. A webhook fires only when needed — saving credits and running instantly.
2️⃣
Run Once before activating. Always test with "Run once" first. Inspect each module's input/output bubbles. Never activate untested scenarios — you'll burn credits on broken logic.
3️⃣
Use Filters aggressively. A filter on a webhook trigger stops useless runs immediately. Filter before you route, before you AI-process, before anything expensive.
4️⃣
Build modular with Subscenarios. Break complex workflows into reusable sub-scenarios. If 3 workflows all need to "Send Slack notification", make it one subscenario — change once, update everywhere.
5️⃣
Map data with the formula editor. Click any field to open the panel. Don't just insert raw variables — use the built-in string, math, and date functions to transform data inline without extra modules.
6️⃣
Use Data Stores as a mini database. Track "already processed" IDs, store config values, remember state between runs. It's free storage built into Make — use it before adding an external database.
7️⃣
Name your modules clearly. Double-click module names to rename them. "Get Email" is useless; "Get Unread Leads from Gmail" is not. Future you will thank you when debugging at 11pm.
8️⃣
Use the HTTP module for any API. If an app isn't in Make's library, use the HTTP module to call any REST API with custom headers, auth, and body. This unlocks every API on the internet.
9️⃣
Set error handlers on critical modules. Add a "Break" or "Resume" error handler to API calls, file operations, and AI modules. Never let one failed module silently kill the entire run.
🔟
Use Make Grid to manage at scale. Once you have 10+ scenarios, open Make Grid for a visual map of your entire automation landscape — see dependencies, health, and relationships at a glance.