A visual automation platform for fixed scenarios and beta agents with explicit data, tool, and usage boundaries.
Workflow & automation · Documented · Documentation checked 2026-10-04
Make scenarios and Make AI Agents (New); connected model providers have their own terms.
Scenario limits vary by plan. AI Agents (New) is in open beta; custom AI providers require a paid plan.
What the platform is for
Make connects modules into scenarios. It can use ordinary transformations, AI steps, or an agent depending on the task. A beginner should learn bundles and mapping first: if you cannot trace a field through the scenario, adding a model makes diagnosis harder.
Know the product boundary
Standard scenarios, AI scenarios, and Make AI Agents (New) differ. The new agent is open beta. Make’s provider and custom-provider paths have different eligibility and billing relationships. Credits describe billing usage, while operations describe module activity.
How the components connect
Modules exchange bundles. Filters enforce route conditions. Error handling manages failed operations. Agents select among named tools and consume input / Knowledge context. Conversation IDs control thread reuse. Structured output supports mapping, while a separate validated human-review state controls consequential actions.
A beginner starting point
Begin with a sample scenario and Run once. Inspect mapped values, add a filter, and test a failure. Then add one bounded AI transformation. Use a read-only beta agent only when it needs to choose tools, and test output validation and external approval before live writes.
Limits and data choices
Agent loops and long inputs can vary cost. A model can return correct-looking fields with false contents. A request to review itself is not an enforced human gate. This edition does not establish a universal native approval feature or cover every integration, module, and enterprise policy.
The technical path
Follow official Make Help for scenarios, modules, errors, current AI Agent configuration, and credit accounting. Advanced integrations need explicit tool contracts and source-service permissions. Deployment means activating a validated scenario with an owner, exception route, and shutdown plan.
Feature map
Scenarios, modules, and mapped data
Move records through a fixed scenario and inspect which values each module receives.
Filters, review gates, and error routes
Route only valid approved records to consequential actions and stop safely on failures.
AI Agents (New): tools and configuration
Configure a beta agent with a bounded goal, named tools, and explicit execution limits.
Knowledge, conversation IDs, and structured output
Distinguish reusable files from run inputs and request an output downstream modules can validate.
Credits, provider billing, and run review
Track scenario usage and model-provider usage as different parts of operating cost.
Complete workflows
Fixed AI triage with a review filter
Classify synthetic requests while keeping authoritative review separate from AI output.
A bounded beta knowledge agent
Use the beta agent to retrieve approved workshop evidence and produce a validated response draft.
Coverage and availability
Models, modes & conversation
Covered: Model provider and beta agent configuration.
Search, research & sources
Covered: Tool-based retrieval / Knowledge; no universal citation guarantee.
Files, analysis & code
Covered: Bundles, mapping, files, and structured output.
Images, video, audio & voice
Covered: Creative operations depend on connected services; native universal media parity not claimed.
Projects, instructions & memory
Covered: Knowledge versus Input files and scoped conversation IDs.
Editing surfaces & deliverables
Covered: Scenario / agent configuration and draft outputs.
Agents, skills, plugins & MCP
Covered: AI Agents (New) tools, scenarios, and MCP; open beta.
Orchestration & scheduling
Not established: Fixed filters / error routes and separate approval state; universal native approval not established.
APIs, SDKs, deployment & evaluation
Not established: Operational usage checks covered; SDK / production integration design deferred.
Sharing, privacy & governance
Not established: Connections, logs, and review ownership; exact enterprise policy matrix deferred.
Plans, devices & accessibility
Not established: Credits and provider billing distinguished; full quotas / accessibility behavior not established.
Sources and verification
Documentation checked 2026-10-04. Examples are illustrative unless described otherwise.
Standard scenarios, AI scenarios, and agents · Make
Filtering bundles · Make
Error handling · Make
Make AI Agents (New) configuration · Make
AI Agent best practices · Make
Credits and provider billing · Make
Make developer documentation · Make