Make AI Agents (New) app

the make ai agents (new) app is available in open beta , so product functionality and pricing may change the app is available on all plans using make's ai provider, with the option to use custom ai provider connections on paid plans make ai agents (new) is an app that creates agents, adds their tools and knowledge, and tests them using a chat interface this article is a reference for its modules and their settings modules the make ai agents (new) app includes the run an agent (new) module run an agent c reate agents, add tools and knowledge, and chat for testing purposes below is a reference for its module settings knowledge upload files so your agent has the additional context to tailor its responses to your goals knowledge files are typically static, for example, company guidelines, glossaries, and style guides see docid\ tcbtvwtxwjamwcfffigy6 for knowledge file limitations add tool provide your agent with tools to perform its tasks tools in {{product name}} are modules, scenarios, and mcp server tools each tool corresponds to a specific module module the module for a specific third party service and action, for example, gmail > send an email scenario the scenarios > call a scenario module mcp server tool the mcp client > call a tool module chat interact with your agent to evaluate its performance before going live send sample tasks and adjust the agent settings based on the results connection select the ai provider that connects your agent to a large language model (llm) the ai provider available depends on your plan make's ai provider is available on all plans custom ai provider connections are available to paid plans model select an llm from the ones that your ai provider offers models vary in processing speed, reasoning abilities, token cost, and effectiveness for specific tasks instructions clearly and systematically describe what the agent does, including its role, behavior, goals, and steps to achieve them the agent follows these guidelines across all tasks input add a specific task or incoming data for the agent to work on map data from previous modules, such as chat messages, emails, customer names, and other values input files upload a file for your agent to process with its task file limitations include make's ai provider, openai, anthropic claude, or gemini only a model that accepts files jpg, png, gif, and pdf for the input files you give the agent pdf, docx, txt, and csv for the output files you ask the agent to generate input files > file name name your file input files > data map the file from a previous download file module, such as google docs > download a file conversation id specify a custom id so your agent keeps user interactions in the same communication thread and remembers them examples a mapped userid to remember conversations with a specific user, in the case of multiple users a mapped timestamp of the first message or email to remember the entire thread and reply a unique combination of characters to remember your requests if you leave this field blank, your agent generates a unique id for each {{scenario singular lowercase}} run and has no memory of previous communication maximum conversation history define the maximum number of replies the agent remembers in a conversation step timeout enter the maximum number of seconds an agent runs in each step before it fails the maximum timeout is 600 seconds (10 minutes) if you leave this field blank, the timeout is the default 300 seconds (5 minutes) response format specify the response format that the agent returns response format > text returns a response in text format response format > data structure returns a response in a custom format, either as output items ( add item ) or as a content type, such as json ( generate ) below is a reference for key fields in the module output to view them, click the output bubble of the run an agent module in the output tab, expand an operation, then a bundle response the agent's answer to the user request map the response to other modules to use it elsewhere metadata the agent's execution steps and token usage summary metadata > execution steps the agent's decision making process in chronological order each step describes factors such as the role behind the step, the tool used, and the tokens consumed metadata > token usage summary the tokens used in a single run, including prompt tokens (input), completion tokens (output), and total tokens to view the reasoning tab of the module output, click the output bubble of the run an agent module and go to the reasoning tab reasoning view how the agent processes data and responds to requests step by step, including the instructions and inputs the agent used to generate a response, and its processing speed in seconds (always shown) what the agent was thinking (shown when using a reasoning model and the task requires deeper reasoning) credit usage https //help make com/credits are the currency you buy and consume to use {{product name}} the make ai agents (new) app, and its knowledge, tools, and chat, each use credits differently credit usage also depends on whether a docid\ hh nrtakeqakbmg63uuin or custom ai provider is selected users on all plans can use make's ai provider users on paid plans can also use custom ai provider connections , such as openai and anthropic claude below is a reference for credit usage, by feature and ai provider connection type source make's ai provider custom ai provider connection run an agent (new) 1 credit per operation + credits based on ai tokens 1 credit per operation chat 1 credit per operation + 1 credit per operation from called tools + credits based on ai tokens 1 credit per operation + 1 credit per operation from called tools knowledge (pdf/docx) 1 credit per operation + 10 tokens per page + credits based on tokens ai tokens for file description generation embedding tokens 1 credit per operation + embedding tokens knowledge (json/csv/txt) 1 credit per operation + credits based on tokens ai tokens for file description generation embedding tokens 1 credit per operation + embedding tokens input files ai tokens based on the file size, type, ai provider, and model ai tokens based on the file size, type, ai provider, and model tools 1 credit per operation and credits based on ai tokens 1 credit per operation the tokens mentioned above refer to the following token types embedding tokens these tokens are used to convert your knowledge file into a searchable format that your agent can query it involves converting chunks of a file into numbers (vectors) to be stored in a rag vector database the number of tokens used depends on the file size, with larger files using more tokens you are billed once, when you upload a file file description ai tokens (make's ai provider only) these tokens are used to generate a file summary based on the first part of the file when you use make's ai provider, make bills you for these tokens if you use a custom ai provider connection, the provider bills you for the tokens