Visual AI automation

How to use
Make.

Building visual automations and bounded AI agents that combine triggers, structured scenarios, knowledge, and tools across business applications.

Open Make ↗ Official download ↗
What it isvisual automation and AI-agent orchestration platform Workflows2 UpdatedJuly 2026

Make is a visual automation and AI-agent orchestration platform. Building visual automations and bounded AI agents that combine triggers, structured scenarios, knowledge, and tools across business applications. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

01

Access & setup

Find, install, and sign in to Make

Get into the official Make experience with the right account and a setup you understand.

  1. 01

    Start at https://www.make.com/ and confirm the domain before entering account or payment information.

  2. 02

    Availability: Make is primarily a browser-based service, with APIs, webhooks, MCP support, and connections to external applications.

  3. 03

    A Make account and team, connections to only the required applications, and an approved AI provider or Make AI Provider configuration.

  4. 04

    Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

  5. 05

    Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

  • Use official download pages.
  • Review permissions during setup.
  • Keep installers and applications updated.
02

First session

Your first useful Make session

Learn the interaction loop using a small task with a clear outcome.

  1. 01

    Choose a low-risk process and decide whether it needs an agent, an AI module, or a deterministic scenario.

  2. 02

    Create a test scenario with one controlled trigger and a narrowly instructed agent.

  3. 03

    Attach a read-only or reversible tool with clear inputs and outputs, then test routine and ambiguous requests.

  4. 04

    Inspect the run history, output, tool choice, credit use, and failure path before enabling the scenario.

  • State the outcome before the background.
  • Provide the real source material.
  • Review the result before expanding the task.
03

Quality control

Check the quality of Make output

Establish that an autonomous run did the right thing, not merely that it finished.

  1. 01

    Define what the run should achieve and what it must never touch before granting it a single tool.

  2. 02

    Read the full execution trace: which tools were called, with what arguments, and in what order.

  3. 03

    Verify the side effects directly in the target system rather than trusting the agent's own report of success.

  4. 04

    Confirm failures surfaced as failures — a silent retry loop or a swallowed error is more dangerous than a crash.

  5. 05

    Re-run the same task and compare: an agent that behaves differently across identical runs is not yet production-ready.

  • Verify side effects in the system of record, not in the agent's summary.
  • Require human approval for any irreversible or outward-facing action.
  • Log every tool call so a run can be reconstructed afterwards.
04

Privacy & permissions

Use Make safely

Bound what an autonomous system can reach before you let it run unattended.

  1. 01

    Enumerate every tool, credential, and system the agent can reach, and remove the ones it does not need.

  2. 02

    Require explicit human approval for irreversible actions: sending, publishing, paying, deleting, or deploying.

  3. 03

    Run against non-production data until behaviour is predictable across repeated runs.

  4. 04

    Set hard limits on spend, iterations, and runtime so a failure loop cannot run unbounded.

  5. 05

    Treat anything the agent reads from the web or a document as data, never as instructions it may follow.

  • Make AI Agent (New) is documented as an open beta and agent outputs are unpredictable. Limit data and connection permissions, distinguish deterministic automation from agentic judgment, validate tool inputs and outputs, require approval for consequential actions, prevent loops and duplicate retries, and monitor retained scenario data and credit use.
  • Follow your organisation's approved-use policy.
  • Never treat fluent output as authorization to act.
05

Core workflows

Step-by-step ways to use Make for the work it does best.

Each workflow is a separate guide with its own steps and review checkpoints.

01 WorkflowBuild a bounded AI agent in Make

Give a Make AI Agent a narrow role, explicit instructions, controlled knowledge, and carefully described tools.

 02 WorkflowRun a reviewed trigger-to-agent workflow in Make

Connect an email, form, chat, webhook, or schedule to an agent while controlling loops, retries, and side effects.

06

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.

Explore the Troiana AI Hub →