Introduction to AI agents
This page reflects a previous version of Make AI Agents. For the latest information, see Make AI Agent (New).
The Make AI Agents app is available on all plans using Make's AI Provider, with the option to use custom AI provider connections on paid plans. The app is available in open beta, so both product functionality and pricing may change.
An AI agent is an autonomous system that acts to achieve its goals while following certain rules. Think of it like a skilled assistant who performs tasks for you after understanding what you want to do.
Make AI agents consist of a few fundamental components that can be thought of as a brain (LLM), instructions (system prompt), memory (context), tools (modules, scenarios and MCP tools), and thinking process (reasoning):
- A Large Language Model (LLM) acts as the agent's brain, powering its reasoning for decision-making.
- The system prompt instructs the agent on how to behave. Like a job description, it defines its role, limitations, and processes.
- Context, or files stored in the agent's long-term memory, provides extra information that helps the agent tailor its responses to your needs. For example, an internal knowledge base or company policies.
- Tools provide the agent with the capabilities to achieve its goals. In Make, those can include modules, scenarios , and MCP tools.
- Reasoning is the agent's thought process when approaching its tasks. When you use a reasoning model in an agent, reasoning reasoning is visible when the agent believes that deeper reasoning is required.
In the next section, you will explore these concepts in more detail.