Make
Also known as: Make AI Agents
Visual automation platform for building multi-step workflows and AI agent flows, with credit-based pricing and a free tier.
Make, formerly known as Integromat, is a visual automation platform that lets people connect thousands of apps and build sophisticated workflows on a drag-and-drop canvas. Founded in 2015 and now part of process-mining company Celonis, it is used by hundreds of thousands of organizations and is known for handling complex, multi-branch logic more visually than most competitors, 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, and Make provides the building blocks for real complexity: a Router for splitting one flow into multiple conditional paths, If-Else and Merge modules, iterators for looping over lists, error handlers with automatic retries, and a replay feature for re-running 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 even write JavaScript or Python inside a flow with Make Code.
Make has leaned heavily into AI while keeping its visual-first identity. Maia is its build-time assistant: 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, Make AI Agents, in their next generation as of early 2026, are autonomous agents that reason at runtime, decide what to do next, and trigger real workflows across thousands of integrations. Crucially, agents are built, run, and debugged inside the same canvas, with a reasoning panel that shows every decision, tool call, and step, so nothing happens behind the scenes.
The agents support multi-modal 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. The throughline is visual orchestration: combining deterministic automation with adaptive AI in a single, transparent landscape.
Vendor details
Canonical URL
https://www.make.com/en/
Category
Agent builder
Company status
acquired
Use cases & customers
Target customers
Deployment options
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.
Agentic Index coverage score
9.0 / 14 capabilities · 64%
| Integrations & Tool CallingAgentic AI Index Expansion Evidence Report | Full |
|---|---|
| Workflow OrchestrationAgentic AI Index Expansion Evidence Report | Full |
| Knowledge Grounding & RAGAgentic AI Index Expansion Evidence Report | Partial |
| Human Oversight & GuardrailsAgentic AI Index Expansion Evidence Report | Unable to verify |
| Security, Identity & GovernanceAgentic AI Index Expansion Evidence Report | Partial |
| Observability & AuditabilityAgentic AI Index Expansion Evidence Report | Full |
| Memory & State PersistenceAgentic AI Index Expansion Evidence Report | Partial |
| Deployment & Data ResidencyAgentic AI Index Expansion Evidence Report | Unable to verify |
| Prebuilt Agents, Templates & PacksAgentic AI Index Expansion Evidence Report | Full |
| Triggers & Channel CoverageAgentic AI Index Expansion Evidence Report | Full |
| Model Flexibility & RoutingAgentic AI Index Expansion Evidence Report | Full |
| APIs, SDKs & MCP ExtensibilityAgentic AI Index Expansion Evidence Report | Full |
| Testing, Debugging & OptimizationAgentic AI Index Expansion Evidence Report | Partial |
| Browser & Computer UseAgentic AI Index Expansion Evidence Report | Unable to verify |
The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify 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
Recent platform changes
Make 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 sourceMake integrated OpenAI's GPT-5.6 model family, including the Sol, Terra, and Luna variants, into its AI Toolkit, OpenAI modules, and AI Agent app. The update allows users to build workflows utilizing the models' 1.05-million context window for complex reasoning or rapid data extraction.
Bears on: Integrations
View sourceMake announced the deprecation of its native Google Chrome app and browser extension, effective August 31, 2026. The retirement is driven by the end of support for Google's Manifest V2. After this date, the extension will be removed from the Chrome Web Store, scenarios relying on the app will stop working, and Make will not offer a replacement module.
Bears on: Browser/computer use
View sourcePricing
From $9/mo · free tier
credits
Included quota
Free ($0): 1,000 credits/mo, 2 active scenarios, 15-min interval, 3,000+ apps. Core ($9/mo annual): 10,000 credits, unlimited active scenarios, 1-min interval, Make API. Pro ($16/mo annual): 10,000 credits + priority scenario execution, custom variables, full-text execution-log search, advanced scheduling/error handling. Teams (~$29/mo annual): + multi-user, team roles, shared scenario templates. Enterprise (custom): custom credit allocation, SSO/SLA, 24/7 support, Value Engineering, enterprise apps (Workday/ServiceNow/Coupa/Greenhouse), custom functions. (Per-tier caps apply; figures vary across sources.)
What is public
Make (make.com, formerly Integromat, now part of Celonis - visual no-code automation, 3,000+ apps) switched from 'operations' to CREDITS on Aug 27, 2025 (1 standard module run = 1 credit; AI/code cost more). Five tiers: Free ($0, 1,000 credits/mo, 2 active scenarios, 15-min interval), Core ($9/mo annual / ~$10.59 monthly, 10,000 credits, unlimited scenarios, 1-min interval), Pro ($16/mo annual, 10,000 credits + priority execution + log search), Teams (~$29/mo annual, + multi-user/roles; possibly per-user), and custom Enterprise. All paid plans start at 10,000 credits and scale via credit packs (extra packs cost ~25% more per credit than the included allotment, standardized Nov 2025). Annual billing saves ~15%.
Billing mechanics
Credit-based: every MODULE action consumes a credit - including triggers, filters, and each iterator loop (an iterator over 10 items = 10 credits). This is more granular than Zapier (where filters are free and only successful actions count). AI modules cost more (e.g., native AI transcription ~50 credits) and Make Code (JS/Python) costs 2 credits per second of execution. The plan sets your monthly credit allowance + features; you estimate cost as records x module-steps-per-record x runs/month. Per-tier caps also apply (figures vary across sources).
Cost watchouts
EVERY module counts - triggers, filters, and iterator loops all burn credits (Zapier's filters are free; Make's aren't), so complex/looping scenarios consume fast; the POLLING TRAP is the killer (a 1-min polling trigger = ~43,200 checks/mo, blowing Core's 10k before any action runs - use webhooks instead); AI modules (~50 credits) and Make Code (2 credits/sec) are credit-heavy; extra credit packs cost ~25% more than included credits (Nov 2025); per-tier caps pause scenarios; Teams may be per-user on some readings; Enterprise climbs sharply
Variable cost rationale
Highly consumption-driven - credits scale with module count x runs, and AI/code modules cost multiples; granular per-module billing gives fine control but demands active monitoring (poorly-built or high-frequency-polling scenarios can burn credits with no useful output)
Additional watchouts
Credit math demands attention - every module (including filters/iterators) and especially polling triggers burn credits; AI/code modules are credit-heavy; caps can pause scenarios (route URLs, not files); fewer native integrations than Zapier; Teams economics weaken past ~5 editors; not ideal for those who 'don't want to think about usage'
Overage / add-ons
When credits run out, scenarios STOP (warnings at 75% and 90%); incoming webhooks queue and resume once credits are added. Options: upgrade tier, buy extra credit packs (1,000 or 10,000), or enable auto-purchase of 10,000 credits (Core/Pro/Teams). Since Nov 2025, extra credit packs cost ~25% more per credit than the plan's included allotment (whether bought manually or auto-purchased). Annual-plan extra credits expire after 12 months (Pro/Teams) vs one month on monthly.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free tier
Lowest paid plan
n/p (exact starter not captured)
Commercial notes
Formerly Integromat (now part of Celonis); the visual 'canvas' leader - branching/looping scenarios that simple trigger-action tools can't do; one of the cheapest serious hosted-automation platforms (Core ~3-5x cheaper than Zapier at equal volume) but with a steeper learning curve; 3,000+ apps (fewer than Zapier's 9,000); credit model rewards technical users who monitor usage; competes with Zapier, n8n, Activepieces, Power Automate, Workato
Key ambiguities
Make switched to credits Aug 2025 (1 module = 1 credit standard, but AI/code differ), which confuses cost estimation; Teams pricing is quoted inconsistently (~$29 vs ~$34-38/mo, and possibly per-user); Enterprise is custom (~$300-$500+/mo estimated start); monthly vs annual rates shift the headline (Core $9 annual vs ~$10.59 monthly); per-tier caps are quoted inconsistently across sources
Cancellation / refund
Permanent Free tier (no card); Core/Pro/Teams self-serve monthly or annual (annual ~15% cheaper; cards/ACH/Google Pay); extra credit packs or auto-purchase available; Enterprise custom (wire/invoice); non-profit discounts; credits expire monthly (or after 12 months on annual Pro/Teams)
Support SLA / resale
Customer support on all plans; priority execution on Pro+; Teams adds collaboration/roles; Enterprise adds SSO, SLA, 24/7 support, a Value Engineering team, and enterprise app integrations (Workday/ServiceNow/Coupa/Greenhouse/Infor M3); Make API on Core+
Missing data
Teams pricing is quoted inconsistently across sources (~$29 vs ~$34-38/mo, possibly per-user); Enterprise is custom (~$300-$500+/mo estimated); exact AI-agent/module credit rates and per-tier caps vary by source. Core starts at $9/mo annual (~$10.59 monthly) for 10,000 credits; paid plans are credit-based (since Aug 2025), Free is a permanent 1,000-credit tier, and AI features/agents consume credits at higher rates.
Related vendors
- Lindy — No-code AI agent builder focused on automating repetitive business…
- Activepieces — Open-source automation platform with a self-hosted Community Edition…
- Adopt AI — No code agent builder that turns existing applications and manual…
- Agent.ai — A marketplace and network of hundreds of prebuilt AI agents plus a…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code enterprise AI platform to build and run AI agents across the…
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.
- AutoGPT10.5 / 14Adds documented Human Oversight & Guardrails and Deployment & Data Residency
- AgentX10.0 / 14Adds documented Human Oversight & Guardrails and Deployment & Data Residency
- Airtable11.0 / 14Adds documented Human Oversight & Guardrails and Deployment & Data Residency
- MindStudio9.0 / 14Adds documented Deployment & Data Residency
- Dify9.5 / 14Adds documented Deployment & Data Residency
- Gumloop11.5 / 14Adds documented Human Oversight & Guardrails and Deployment & Data Residency
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded