Make
Also known as: Make AI Agents, Make AI Agent (New), Integromat, Maia, Make Grid, Make Skills
Visual automation platform for building multi step workflows and AI agent flows, with pricing based on credits and a free tier.
Make, formerly known as Integromat, is a visual automation platform that lets people connect thousands of apps and build workflows on a drag and drop canvas. Make was founded in 2015 and is now part of Celonis, the process mining company. It is used by hundreds of thousands of organizations. It handles complex logic with many branches visually, with each step laid out as a module you can see and inspect.
The heart of the product is the Scenario Builder. A scenario chains modules together from a library of several thousand app integrations. A Router splits one flow into multiple conditional paths, If-Else and Merge modules handle conditions, iterators loop over lists, error handlers retry automatically, and a replay feature reruns a scenario against past data to fix and validate logic. Teams can turn any scenario into a reusable function, share scenarios with a single link, and write JavaScript or Python inside a flow with Make Code.
Maia is Make's assistant for building automations. You describe an automation in plain language, and Maia proposes and wires up a scenario conversationally, asking clarifying questions, while every module it places stays visible and editable on the canvas. Separately, the new generation of Make AI Agents are autonomous agents that reason at run time, decide what to do next, and trigger real workflows across thousands of integrations. Agents are built, run and debugged inside the same canvas, with a reasoning panel that shows every decision, tool call and step.
The agents support multimodal inputs and outputs like PDFs, images and CSVs, can be shared and reused across teams, and draw on a Library of ready made examples. A Module Tools feature turns any module into a callable agent tool, and Make supports the Model Context Protocol so its automations can act as tools for external AI systems. Deterministic automation steps and agent reasoning combine in one flow on the same canvas.
Vendor details
Canonical URL
https://www.make.com/en/
Category
Agent builder
Subcategory
Visual automation platform with runtime AI agents built on the scenario canvas
Funding status
Acquired. Make, founded in 2015 as Integromat, is part of Celonis, the process-mining company; Celonis appears in the trust domain and copyright line on Make's own security page.
Company status
acquired
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Agents draw tools from the same module library as Make's deterministic automation product. The four tool classes are individual modules, whole scenarios, MCP server tools and other agents. MCP works in both directions. The Make MCP server exposes automations to external AI systems, and MCP toolboxes group tools for agents. AI providers are OpenAI, Gemini and Anthropic Claude, plus Make's own AI provider, which needs no customer provider account. Custom provider connections are available on paid plans, and a separate Make Grid surface connects external providers. The wider catalog spans thousands of app modules across CRM, communications, storage, databases and productivity tools, including modules that trigger Zapier and n8n. Data stores provide durable structured storage across runs, and cryptographic modules cover AES, PGP, RSA signatures and salted hashing. Custom apps can be built through the Make Developer Hub, which also holds the API documentation.
In practice
One lead trigger needs to branch three ways based on location and an AI intent check. Make's Router and If-Else modules split a single scenario into conditional paths on the canvas, instead of three separate workflows.
You want an AI agent but won't trust one whose decisions you can't see. Make builds agents inside the same visual canvas, with a reasoning panel showing every decision and tool call step by step.
A new automation idea is clear in your head but tedious to wire up. Maia lets you describe it in plain language and builds the scenario conversationally, leaving every module visible and editable before it runs.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
Agent tools are modules, scenarios, MCP server tools and other agents, drawn from Make's app and module catalog, and they connect agents to third party services such as email, database and CRM systems to carry out tasks. Scenarios become tools with defined inputs and outputs, and MCP toolboxes group tools. Sourcehelp.make.com Introduction to Make AI Agent (New) and Scenarios for AI agentsread 2026-09-30 |
|
| Workflow Orchestration | Full |
|
Agents call other agents, scenarios and modules as tools, and agents run inside scenarios, whose engine routes and branches between modules and handles failures through an error handling tree (error handlers, exponential backoff, throw), so deterministic steps and agent reasoning combine in one flow. Sourcehelp.make.com Introduction to Make AI Agent (New) and error handling treeread 2026-09-30 |
|
| Knowledge Grounding & RAG | Full |
|
Knowledge files are stored in a retrieval augmented generation vector database. Make splits each file into chunks, converts them to vectors and returns the most relevant chunks to the agent at request time, not the whole file. Files of up to 20 MB, 20 per agent, in TXT, PDF, DOCX, CSV, MD or JSON format, are managed at organization level, can be downloaded, replaced and deleted, and are deleted after 180 days without a query. Sourcehelp.make.com Knowledge files for AI agentsread 2026-09-30 |
|
| Human Oversight & Guardrails | Partial |
|
The customer controls which modules, scenarios and MCP tools an agent may call, and Make's best practices treat minimal access as the most reliable constraint, alongside prompt instructions to have a person validate outputs, which Make warns agents may not always follow. No approval, checkpoint or pause for a person is described for Make AI Agent (New). Sourcehelp.make.com Make AI Agent (New) app and AI agent best practicesread 2026-09-30 |
|
| Security, Identity & Governance | Full |
|
Make's information security program is ISO 27001 certified, and Make has completed SOC 2 Type II and SOC 3 audits and adheres to GDPR. The SOC 2 report details internal controls, and a product-specific public SOC 3 summary is available at trust.celonis.com/product/make/soc-3. Controls include single sign-on with Google, Facebook and GitHub, with Enterprise customers able to use their own SSO, advanced role and team management within an organization profile, log retention beyond the 30-day default on Enterprise, and a hosting environment reachable only from the private network over VPN, with no direct public internet access. The program also covers regular independent penetration testing, vulnerability management, OWASP-aligned coding standards with static application security testing, AES-256 full-disk encryption with AWS KMS, TLS 1.2 and 1.3 in transit, a public bug bounty and an enterprise security whitepaper. Sourcemake.com security pageread 2026-09-01 |
|
| Observability & Auditability | Full |
|
Each agent run returns metadata with its execution steps and token usage, and a Reasoning tab shows processing steps, speed, context window use and any fallback connection, with the agent's step by step decisions available for debugging. Agents run as modules inside scenarios, which keep the platform's run records and error handling. Sourcehelp.make.com Make AI Agent (New) app and Introduction to Make AI Agent (New)read 2026-09-30 |
|
| Memory & State Persistence | Partial |
|
The Run an agent module takes a Conversation ID that keeps a user's interactions in the same thread across runs, with a maximum conversation history setting. No scope beyond the thread, retention or delete path is described for that history. Data stores persist between scenario runs, but they are application data the builder reads and writes, not a memory layer. Sourcehelp.make.com Make AI Agent (New) app and data storesread 2026-09-30 |
|
| Deployment & Data Residency | Partial |
|
An on-prem agent ships as downloadable installers for Windows Server and for Debian, Ubuntu, Fedora and Red Hat, needs Java 11 or above and is configured with a client ID, secret and base URL, so a customer can run an execution component inside its own infrastructure without a sales conversation, though it is still in beta. The Enterprise platform runs in a separately managed AWS environment isolated from self-service cloud customers, and log data is kept for 30 days by default, with longer retention on Enterprise. The cluster runs across two zones on AWS EC2 private instances within an Amazon VPC. No region choice or residency option is offered, and the platform itself is not self-hostable. Sourcemake.com on-prem agents and security pagesread 2026-09-01 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
The AI Agents Library offers pre-made AI agent scenarios as starting points, among them Account Researcher, Lost Deals Analysis, Resume Analysis, Sales Coach, Lead Qualification, Personalized Outreach, Interview Scheduler, Customer Feedback, HR Onboarding Q&A and Competitor Price Monitor agents, each doing its own job. Sourcemake.com AI agents libraryread 2026-09-30 |
|
| Triggers & Channel Coverage | Full |
|
Agents start from the first module of their scenario, with guided examples for chat messages, Slack and Telegram messages, emails and mailhooks, form submissions and webhooks, and they can also run on their own on a schedule. Sourcehelp.make.com Create AI agents for different triggersread 2026-09-30 |
|
| Model Flexibility & Routing | Full |
|
An AI provider connects the agent to a model, with OpenAI, Gemini and Anthropic Claude named as common providers. Make's own provider needs no provider account, custom AI provider connections are available on paid plans, and the Run an agent module takes a connection and a model selection. Sourcehelp.make.com Introduction to Make AI Agent (New) and Make AI Agent (New) appread 2026-09-30 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
The Make MCP server lets MCP clients such as Claude and ChatGPT run scenarios and manage the Make account, including checking data stores and inviting organization members, with MCP toolboxes limiting which scenarios are exposed. The Make Developer Hub has the API documentation and the path for building custom apps. Sourcehelp.make.com Make MCP server and developers.make.com API documentationread 2026-09-30 |
|
| Testing, Debugging & Optimization | Partial |
|
Debugging tools include the reasoning view, which explains each decision and helps when something goes wrong, the error handling tree, a common errors guide and advice to monitor agent behavior through output bundles. No evaluation, scoring, test dataset or regression testing is described. Sourcehelp.make.com Introduction to Make AI Agent (New), AI agent best practices and error handling treeread 2026-09-30 |
|
| Browser & Computer Use | Not documented |
|
Agent tools are modules, scenarios, MCP server tools and other agents, and no browser, desktop or computer use is described for Make AI Agent (New). Web content reaches scenarios through app modules and HTTP requests, not through a browser Make runs for the agent. Sourcehelp.make.com Introduction to Make AI Agent (New) and Make AI Agent (New) appread 2026-09-30 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Scenarios in Make can now include Claude browsing the web, through a new Browser Use Tool option in the Anthropic Claude app's Create a Prompt module. The model can navigate websites, extract text and manage browser tabs as a step in an automation. New fields carry the browsing session from one scenario step to the next, and a tool result can now be flagged as an error so the model gets better feedback.
Bears on: Browser/computer use
View sourceMaia, the AI that builds scenarios in Make, now has a Plan mode that asks its questions up front, lays out the modules, assumptions and approach, and builds nothing until the user approves, checking connections, app capabilities and plan tier access along the way. Maia also gains Memory, which carries a user's preferences between scenarios and can be edited or erased, image attachments for building from a sketch or screenshot, and Resolve error, which reads a failed run's data and proposes a fix the user reviews before saving.
Bears on: Human approval / guardrails
View sourceMake introduced Private spaces, giving each team member an isolated workspace where their scenarios, connections, and module settings are from others. The feature also includes admin controls for Enterprise plans, such as read-only visibility into private spaces and the ability to set individual credit limits.
Bears on: Security / enterprise
View sourcePricing
Core $12, Pro $21 and Teams $38 per month billed monthly, each with 10,000 credits, and 15% or more off billed annually. A free plan includes 1,000 credits a month. Enterprise is custom.
Credits. Each plan carries a monthly credit allowance, and every module action in a scenario uses credits.
Included quota
The Free plan includes 1,000 credits a month, 2 active scenarios, a 15 minute minimum interval, a 5 minute maximum execution time and 512 MB of data transfer. Core ($12 a month), Pro ($21) and Teams ($38) each include 10,000 credits a month on monthly billing. Enterprise is custom.
What is public
Make publishes a free plan with 1,000 credits a month, no time limit, 2 active scenarios and a 15 minute interval, and three paid plans billed monthly at Core $12, Pro $21 and Teams $38, each starting at 10,000 credits. Annual billing takes 15% or more off. Enterprise is custom through sales.
Billing mechanics
Billing is credit based. Every module action uses a credit, including triggers, filters and each pass of an iterator, so an iterator over 10 items uses 10 credits. AI modules cost more (native AI transcription uses about 50 credits), and Make Code in JavaScript or Python costs 2 credits per second of execution. The plan sets the monthly credit allowance and the features. Monthly credit use comes to records times module steps per record times runs a month. Each tier also caps data transfer.
Cost watchouts
Every module counts. Triggers, filters and iterator loops all use credits, so complex or looping scenarios consume them fast. Polling is the largest drain: a trigger that polls every minute makes about 43,200 checks a month, which uses up Core's 10,000 credits before any action runs. Webhook triggers run only when data arrives, so they avoid that draw. AI modules (about 50 credits) and Make Code (2 credits a second) are credit heavy. Extra credit packs cost about 25% more than included credits. Data transfer caps on each tier pause scenarios. Paid plans list unlimited users, and Enterprise is custom priced.
Variable cost rationale
Credits are metered per module action, so the bill grows with the number of modules in a scenario times the number of runs. AI modules and Make Code cost several credits per action, and a scenario that polls often or is badly built can use credits with no useful output. Each plan carries a fixed monthly credit allowance, with warnings at 75% and 90%, and scenarios stop when it runs out unless extra credit packs or automatic purchase are switched on. Extra credits cost about 25% more per credit than included ones and expire, and Enterprise is custom.
Additional watchouts
Cost depends on credit math. Every module, filters and iterators included, uses credits, and polling triggers use the most. AI and code modules are credit heavy. Data transfer caps can pause scenarios, and passing file URLs rather than the files themselves keeps transfer down.
Overage / add-ons
When credits run out, scenarios stop, after warnings at 75% and 90%. Incoming webhooks queue and resume once credits are added. More credits come from a higher tier, extra credit packs of 1,000 or 10,000, or automatic purchase of 10,000 credits on Core, Pro and Teams. Extra credit packs cost about 25% more per credit than the plan's included credits, whether bought by hand or automatically. Extra credits on annual Pro and Teams plans expire after 12 months, against one month on monthly billing.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan with 1,000 credits a month and no time limit, 2 active scenarios, a 15 minute minimum interval and a 5 minute maximum run time
Lowest paid plan
Core at $12 per month billed monthly, with 10,000 credits
Commercial notes
Formerly Integromat, and part of Celonis. A visual scenario builder with branching and looping, billed in credits that reward users who monitor usage.
Key ambiguities
Credit consumption per module, and higher rates for AI and code modules, make cost estimation depend on scenario design. The discounted annual prices are not published, only the saving of 15% or more.
Cancellation / refund
Core, Pro and Teams bill monthly or annually, with annual 15% or more cheaper, and cancel any time, running to the end of the term before moving to the Free plan. Enterprise is custom and invoiced, and non-profit discounts exist.
Support SLA / resale
Every plan has customer support, and Pro and above get priority execution. Enterprise adds SSO, an SLA, 24/7 support, a Value Engineering team and enterprise app integrations such as Workday, ServiceNow, Coupa, Greenhouse and Infor M3.
Missing data
Annual per month prices are not published, and Enterprise pricing is custom.
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agenta — Agenta is an open source workspace where teams build AI agents by…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
Alternatives to Make
The closest documented capability profiles to Make among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Airtable11.0 / 14Matches Make across all 14 documented capabilities
- Dify12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Deployment & Data Residency
- DronaHQ11.0 / 14Fuller documented coverage on Testing, Debugging & Optimization
- LuMay12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Deployment & Data Residency
- Moveo.AI12.0 / 14Fuller documented coverage on Deployment & Data Residency and Testing, Debugging & Optimization
- Pickaxe10.0 / 14A lighter documented profile than Make
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded