--- title: Create your first AI agent slug: create-your-first-ai-agent description: Build your first AI agent: plan your agent, configure instructions, add tools and knowledge, and test before going live. image: https://archbee-image-uploads.s3.amazonaws.com/oAyFj2GHlBeBVWF5OAir2/J-O5FIDw4BFeGjE6q-74n_5.png docTags: createdAt: 2026-01-19T09:57:40.833Z --- In this guide, learn how to create your first agent in Make. The process includes these steps: 1. **Plan an agent **so you have a framework to build from. 2. **Build the scenario **where the agent lives. 3. **Configure the agent **so it understands its job and how to do it. 4. **Add the agent's tools **so it has the capabilities to perform its tasks. 5. **Add the agent's knowledge **so it has additional context to tailor its responses. 6. **Test the agent **so it performs as expected before going live. Once you complete the steps, you'll have a working agent ready to use in your scenarios. :::ExpandableHeading ## Step 1. Plan your AI agent Plan your agent so you know what it does, the tools and knowledge it needs, and what triggers it, for example: - **What the agent does: **Content marketing specialist who creates blogs for social media based on trending industry topics - **Tools:** Google Drive, Airtable, LinkedIn, and Facebook modules - **Knowledge:** The company style guide and product glossary - **Trigger:** Google Sheets document with trending topics ::: ::::::ExpandableHeading ## Step 2. Build your AI agent scenario In Make, your agent belongs to a scenario. To start building, sign in to Make and click **Create scenario** at the top. ### Add a trigger Your AI agent scenario typically starts with a trigger. A [trigger ](https://help.make.com/types-of-modules#triggers)is the module that starts the scenario and determines how the agent receives new requests or information. To add a trigger module: :::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, click the giant plus. ::: :::WorkflowBlockItem In the app search, enter the name of the third-party service you need, such as **Gmail **or **Google Sheets**, and click its app. ::: :::WorkflowBlockItem Select the module that corresponds to the action you need, for example, **Watch Changes** or **Search Rows**. ::: :::WorkflowBlockItem Click the module, configure it based on your requirements, and save. ::: :::WorkflowBlockItem Click the clock icon on the module. ::: ::::WorkflowBlockItem In **Schedule settings**, configure how often the scenario runs. :::hint{type="info"} The option to start the scenario immediately when new data arrives is only available in [instant triggers](https://help.make.com/types-of-modules#instant-triggers), which are marked with an instant tag. For information on all scheduling options, see [Schedule a scenario](https://help.make.com/schedule-a-scenario). ::: :::: :::WorkflowBlockItem Click **Save **on the Scenario toolbar. ::: ::::: You've now added a trigger to the AI agent scenario. ### Add more modules (optional) Optionally, add more modules before the agent. Certain use cases require additional modules, such as providing your agent information that frequently changes. Download file, web search, and chat message modules are examples of modules you can add. To add more modules: ::::WorkflowBlock :::WorkflowBlockItem Click the plus icon next to the trigger. ::: :::WorkflowBlockItem In the app search, enter the name of the third-party service you need, and click its app. ::: :::WorkflowBlockItem Select the module that corresponds to the action you need. ::: :::WorkflowBlockItem Click the module and configure it based on your requirements. ::: :::WorkflowBlockItem Click **Save**. ::: :::WorkflowBlockItem Click **Save **on the Scenario toolbar. ::: :::WorkflowBlockItem Repeat steps 1-5 for any other modules you want to add. ::: :::: Once the other modules ready, you can add the agent. Optionally, return to this step at the end to add a module after the agent. ### Add your AI agent To add the **Make AI Agent (New)** > **Run an agent **module to your scenario: ::::WorkflowBlock :::WorkflowBlockItem Click the plus icon on the right side of the last module in your scenario. ::: :::WorkflowBlockItem Search for **Make AI Agent (New) **and click the app. ::: :::WorkflowBlockItem Click the** Run an agent **module. ::: :::: You've now added the **Make AI Agent (New)** > **Run an agent **module to your scenario. Next, configure its settings. :::::: ::::::ExpandableHeading ## Step 3. Configure your AI agent In the module settings of the **Make AI Agent (New)** > **Run an agent **module, configure the agent's AI provider and model, instructions, and other specifics. ### Choose an AI provider and model AI providers, such as Make's AI Provider, OpenAI, and Claude, connect your agent to large language models (LLMs). To choose your AI provider and model: :::::WorkflowBlock :::WorkflowBlockItem In **Connection **in the **Make AI Agent (New)** > **Run an agent **module, click **Add **to create a new AI provider connection, or select an existing one from the dropdown. ::: ::::WorkflowBlockItem Select an AI provider connection from the **Connection type **dropdown. :::hint{type="info"} If you're on a **Free plan**, select Make's AI Provider. If you're on a **paid plan**, select Make's AI Provider or a custom AI provider connection, such as OpenAI or Anthropic Claude. ::: :::: :::WorkflowBlockItem Name the connection and configure the remaining fields. If the connection requires an API or access key, obtain the key from your AI provider account. ::: :::WorkflowBlockItem Click **Save**. ::: ::::WorkflowBlockItem From the **Model **dropdown, select a model. The AI provider offers the models listed. :::hint{type="info"} Models vary in processing speed, reasoning abilities, token costs, and effectiveness in specific tasks. Research the models available to decide which best fits your goals. ::: :::: ::::: Your agent now has an AI provider and model for its decision-making. ### Add instructions Instructions tell the agent what its job is and how to do it. The agent follows these rules across all tasks and requests. In **Instructions**, clearly and systematically outline the agent's role, behavior, goals, and the steps to achieve them. ### Add inputs and files Specify the inputs that the agent processes in each scenario run. Optionally, add input files to process with the inputs. To add inputs and files: :::::WorkflowBlock :::WorkflowBlockItem In the **Make AI Agent (New) **> **Run an agent (New) **module, in **Input**, add any specific, one-time requests or mapped data from previous modules. ::: ::::WorkflowBlockItem Optionally, in **Input **files, add the file that the agent receives from a previous module to process with its inputs: 1. In **File name**, name the file to identify it later. 2. In **Data**, click the text field and map the file from the module that downloads files. :::hint{type="info"} **File requirements** To input files to the agent, you must select Make's AI Provider, OpenAI, Anthropic Claude, or Gemini, and a model that supports files. To learn more about supported file formats, see [Input files for AI agents](docId\:EtjXD5CKUre4KBFRmAdfP). ::: :::: ::::: You've now added inputs and files to your agent. ### Add additional specifics (optional) In the remaining fields, configure any additional settings, such as: - Conversation ID - Maximum conversation history - Step timeout - Response format To add these specifics: :::::WorkflowBlock :::WorkflowBlockItem In the **Make AI Agent** >** Run an agent **module, in **Conversation ID**, specify a custom ID so your agent remembers your interactions in a single thread and can reply to them. ::: ::::WorkflowBlockItem Alternatively, map a thread ID or timestamp from a previous module, such as the thread ID of an email or Slack message. :::hint{type="info"} If you leave the **Conversation ID** blank, the agent has no memory of your previous interactions and generates a new ID with each run. ::: :::: :::WorkflowBlockItem Toggle **Advanced settings **for more setting options. ::: :::WorkflowBlockItem If you added a Conversation ID, specify in **Maximum conversation history **the maximum number of replies the agent remembers in the conversation. ::: :::WorkflowBlockItem In **Step timeout**, enter the maximum number of seconds an agent runs in each step before it fails. If you leave this field blank, the default time is 300 seconds (5 minutes). ::: :::WorkflowBlockItem In **Response format**, specify the response format that the agent returns. - Select **Text **in the dropdown to return text as output. - Select **Data structure** in the dropdown to return responses in a custom structure that you define. ::: :::WorkflowBlockItem Click **Save**. ::: ::::: You've now configured your agent. Adjust its settings at any time. :::::: ::::::ExpandableHeading ## Step 4. Add tools Give your agent modules, scenarios, MCP servers, and other agents to use as tools. ### Add modules A module is a built-in or third-party app that performs a specific action. Add modules as agent tools for one-step tasks, such as monitoring new customer contacts, sending emails, downloading files, or updating spreadsheets. To add a module as a tool: :::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, hover over the plus icon of the** Make AI Agent (New)** > **Run an agent **module, and click **Add tool**. ::: :::WorkflowBlockItem In the app search, enter the name of the third-party service you need, such as Gmail, and click its app. ::: :::WorkflowBlockItem Select the module for the action you need. ::: :::WorkflowBlockItem Click the module, configure it according to your requirements, and save. ::: :::WorkflowBlockItem Optionally, to filter outputs, click the **Tool settings** label on the route between the agent and module. ::: ::::WorkflowBlockItem In **Tool outputs**, select the outputs to return to the agent. :::hint{type="info"} Make automatically excludes internal metadata from the tool output. Re-include it now if the agent needs it. ::: :::: ::::: You've now added a module as a tool for your agent. ### Add scenarios Scenarios are automated workflows consisting of multiple modules. Add scenarios as agent tools for more complex tasks that include several steps or third-party services. You have two ways to add a scenario as a tool: choose an existing scenario or create a new one. **To choose an existing scenario:** :::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, hover over the plus icon of the **Make AI Agent (New)** > **Run an agent** module, and click **Add tool**. ::: :::WorkflowBlockItem In the app search, search for and click **Scenarios**. ::: :::WorkflowBlockItem Select the **Call a scenario** module. ::: ::::WorkflowBlockItem Select an existing scenario from the **Scenario** dropdown. :::hint{type="info"} If you want the scenario to return data to the agent, the scenario must end with a **Return outputs **module. ::: :::: :::WorkflowBlockItem In **Description**, describe what the scenario does and when the agent uses it. ::: :::WorkflowBlockItem In **Wait for the scenario to finish**, select **Yes** if you want to wait for the called scenario to finish its run or return output before continuing this scenario's run. ::: :::WorkflowBlockItem Click **Save**. ::: ::::: You've now added an existing scenario as a tool for your agent. **To create a new scenario:** ::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, hover over the plus icon of the **Make AI Agent (New)** > **Run an agent **module, and click **Add tool**. ::: :::WorkflowBlockItem In the app search, search for and click **Scenarios**. ::: :::WorkflowBlockItem Select the **Call a scenario** module. ::: :::WorkflowBlockItem From the **Scenario** dropdown, click **Create scenario**. ::: :::WorkflowBlockItem Name your scenario, for example, "Watches new rows and sends emails." ::: :::WorkflowBlockItem Describe what the scenario does so the agent knows when to use it, for example, "Watches new rows in Google Sheets and sends a welcome email to new customers." ::: :::WorkflowBlockItem Define scenario inputs and outputs. Inputs are data parameters that the agent fills when it calls the new scenario, and outputs are data that the new scenario returns to the agent. Examples: - **Input items:** Customer email address, first name, last name, email body, and row ID from a spreadsheet - **Output items: **Email timestamp and success status ::: :::WorkflowBlockItem Click **Create scenario**. ::: :::WorkflowBlockItem In the new scenario, add the modules you need between the **Scenarios **modules. ::: :::WorkflowBlockItem Configure the added modules, including mapping the previously defined scenario inputs to the relevant fields. ::: :::WorkflowBlockItem In the **Scenarios **>** Return output** module, map the scenario outputs. ::: :::WorkflowBlockItem On the Scenario toolbar, toggle **On demand** to activate the scenario and allow the agent to call it when needed. ::: :::WorkflowBlockItem Click **Save**. ::: :::: You've now added a new scenario as a tool for your agent. ### Add MCP servers Give your agent access to tools from third-party MCP servers when the actions that you want it to perform are unavailable through the standard Make apps. To add an MCP server as a tool: :::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, hover over the plus icon of the **Make AI Agent (New) **> **Run an agent** module, and click **Add MCP**. ::: :::WorkflowBlockItem In **Connection**, click **Add** to create a connection to an MCP server, or select an existing connection from the dropdown. ::: ::::WorkflowBlockItem In **Tools**, select the MCP tools you want the agent to access, or click **Select All** to select all tools. :::hint{type="info"} Multiple MCP servers and tools may result in high AI token usage. Limit MCP servers and tools to what the agent needs to perform its tasks. ::: :::: :::WorkflowBlockItem Click **Save**. ::: ::::: You've now added an MCP server as a tool for your agent. ### Add agents Add other agents as tools if you want your agent to delegate tasks to sub-agents. :::hint{type="info"} Agent nesting is limited to one level; a parent agent can have a sub-agent, but a sub-agent can't have another sub-agent. ::: To add an agent as a tool: :::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, hover over the plus icon of the **Make AI Agent (New)** > **Run an agent** module, and click **Add tool**. ::: :::WorkflowBlockItem In the app search, find the **Make AI Agent (New)** > **Run an agent**. ::: ::::WorkflowBlockItem In **Tool settings**, give the agent a name and a description in **Tool name** and **Tool description**. :::hint{type="info"} The parent agent uses the sub-agent name and description to understand what the sub-agent does. It doesn't see the sub-agent's instructions or tools. ::: :::: :::WorkflowBlockItem In **Connection**, click **Add** to create a new AI provider connection, or select an existing one from the dropdown. ::: :::WorkflowBlockItem In **Model**, select a model or **Let AI Agent decide**. ::: :::WorkflowBlockItem In **Instructions**, outline this agent's role and behavior. ::: :::WorkflowBlockItem In **Input**, select **Let AI Agent decide**. ::: :::WorkflowBlockItem In **Input files**, select **Let AI Agent decide**. ::: :::WorkflowBlockItem In **Conversation ID**, select **Let AI Agent decide** to generate a new conversation ID per run, or enter a specific ID to allow the parent agent and sub-agent to continue their conversation across runs. ::: :::WorkflowBlockItem Optionally, to filter outputs, click the **Tool settings** label on the route between the parent agent and this agent. ::Image[]{src="https://api.archbee.com/api/optimize/oAyFj2GHlBeBVWF5OAir2/LcULzqGNLJpasxBqM92-b_tool-outputs.png" size="60" isUploading="false" position="center" width="1118" height="925" darkWidth="1118" darkHeight="925" showCaption="false"} ::: ::::WorkflowBlockItem In **Tool outputs**, select the outputs to return to the parent agent. :::hint{type="info"} Make automatically excludes internal metadata fields for sub-agent tools. You can re-include them in outputs or exclude other fields. ::: :::: ::::: You've now added an agent as a tool for your agent. :::::: ::::::ExpandableHeading ## Step 5. Add knowledge [Knowledge](docId\:TCBtvwTxWJamwcfffIgy6) is reference information that the agent uses to tailor its responses to your goals. Knowledge files are typically static, such as company guidelines or glossaries. The agent stores files in a RAG vector database, retrieving relevant parts based on your request. You have two ways to add knowledge files to your agent: - Directly with the **Make AI Agent (New)** app for static files and a quick setup - With the **Knowledge **app for files that update frequently :::hint{type="info"} Before adding a file to your agent, give it a name that clearly decribes what it contains. ::: ### With the Make AI Agent (New) app To add knowledge files directly with the **Make AI Agent (New)** app: :::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, hover over the plus icon of **Make AI Agent (New)** > **Run an agent** module, and click **Knowledge. ** ::: :::WorkflowBlockItem In **Knowledge files**, click **Upload files**. ::: ::::WorkflowBlockItem Click** Choose file** to select a file to upload. Supported file types include JSON, TXT, CSV, and PDF. :::hint{type="info"} File upload consumes tokens for converting file content to vectors and generating file descriptions. Tokens vary based on file size. ::: :::: :::WorkflowBlockItem Click **Save**. ::: :::WorkflowBlockItem Click the pencil icon next to your added file. ::: :::WorkflowBlockItem Optionally, in **Description**, edit the AI-generated description of your file, or leave it as is. ::: :::WorkflowBlockItem Click **Save**. ::: :::WorkflowBlockItem Toggle** Advanced settings** for more file settings. ::: :::WorkflowBlockItem Optionally, specify a search query that the agent uses to find information in your file, or allow the agent to decide the query (recommended). ::: :::WorkflowBlockItem Optionally, specify the number of results (relevant chunks of the file) the agent returns, or allow the agent to decide the number (recommended). ::: :::WorkflowBlockItem Click **Save**. ::: ::::: You've now added a knowledge file to the agent. ### With the Knowledge app You can add knowledge files with the **Knowledge **app in your main scenario, or in a separate one dedicated to uploading and managing knowledge. To avoid uploading files each time the main scenario runs, create a separate scenario: ::::WorkflowBlock :::WorkflowBlockItem In a new tab, click **Create scenario** at the top. ::: :::WorkflowBlockItem In the Scenario Builder, click the giant plus. ::: :::WorkflowBlockItem In the app search, search for and click the name of the third-party service that downloads a file, such as Google Drive or Gmail. ::: :::WorkflowBlockItem Select the download file module, such as the **Google Drive** > **Download a File** module. ::: :::WorkflowBlockItem Configure the download file module settings and click **Save**. ::: :::WorkflowBlockItem Click **Save **on the Scenario toolbar. ::: :::WorkflowBlockItem Click **Run once **to get mappable data for later modules. ::: :::WorkflowBlockItem Click the plus icon next to the download file module. ::: :::WorkflowBlockItem In the app search, search for and click the **Knowledge** app. ::: :::WorkflowBlockItem Select the **Upload knowledge** module. ::: :::WorkflowBlockItem In **File name**, map the output value from the download file module that corresponds to the file name, for example, `Name`. ::: :::WorkflowBlockItem In **File content**, map the output value from the download file module that corresponds to the file content, for example, `Data`. ::: :::WorkflowBlockItem Click **Save**. ::: :::WorkflowBlockItem Click **Run once **to upload the knowledge file. ::: :::: You've now added knowledge to your agent in a separate scenario. :::hint{type="info"} Alternatively, to add knowledge with the **Knowledge **app in your main scenario, add the download file and **Knowledge **> **Upload knowledge** modules after the **Make AI Agent (New)** > **Run an agent** module. ::: :::::: :::::ExpandableHeading ## Step 6. Test your AI agent Once you've created your agent, test how well it performs its tasks. You have a few ways to test agents in Make: - Chat with the agent - Run the scenario - Disable tools - View previous scenario run details ### Chat with the agent Chat is an interface where you send sample requests to your agent to test its performance. To chat with the agent: ::::WorkflowBlock :::WorkflowBlockItem Hover over the plus icon of the **Run an agent** app and click **Chat**, or right-click the **Run an agent** app and select **Chat with Agent**. ::: :::WorkflowBlockItem Enter a request, for example, "What is my recipe for this week?" ::: :::WorkflowBlockItem The agent calls the relevant tools and returns a response. If the called tools have a red error symbol, expand a tool and view its output. ::: :::WorkflowBlockItem Adjust your agent's settings, tools, or knowledge based on the results. ::: :::WorkflowBlockItem Return to the chat and resend the sample request. ::: :::WorkflowBlockItem Repeat steps 3-5 until the agent performs as expected. ::: :::: You've now used chat to test your agent. ### Run the scenario Test your agent directly in the Scenario Builder using trigger data from previous scenario runs. To run the scenario with existing data: ::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, click the downward arrow next to** Run once**. ::: :::WorkflowBlockItem From the **Scenario run **dropdown, select a previous scenario run to use for test data. ::Image[]{src="https://api.archbee.com/api/optimize/oAyFj2GHlBeBVWF5OAir2/qHAzfpdsCNZ2LPwOv3u6u-20260126-132409.png" size="60" width="576" height="498" darkWidth="576" darkHeight="498" position="center" showCaption="false"} ::: :::WorkflowBlockItem Click **Run once**. ::: :::WorkflowBlockItem Repeat steps 1-3 until the agent performs as expected. ::: :::: You've now run your scenario using existing data. ### Disable a tool Disable one or more tools to check how the agent performs without them. The agent only calls enabled tools. To disable a tool: ::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, right-click the route of the tool you want to disable. ::: :::WorkflowBlockItem Click **Disable tool**. ::Image[]{src="https://api.archbee.com/api/optimize/oAyFj2GHlBeBVWF5OAir2/zbL6Zdv2sTZKNulwOI04R-20260522-084551.png" size="60" width="1002" height="696" position="center" darkWidth="1002" darkHeight="696" showCaption="false"} ::: :::: You've now disabled a tool. To enable it, right-click the same route and click **Enable tool**. ### View scenario run details View previous scenario runs in detail to understand how to resolve the errors that your agent or its tools return. To view Scenario run details: ::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, click the back arrow next to the scenario name. ::: :::WorkflowBlockItem Click **History**. ::: :::WorkflowBlockItem Next to the scenario run with an **Error **status, click **Details**. ::: :::WorkflowBlockItem In the Run details, click the output bubble. ::: :::WorkflowBlockItem To view outputs, expand an operation in the **Output** tab. Some key fields to focus on include **Response **and **Metadata **> **Execution steps**. ::: :::WorkflowBlockItem To view the agent's thought process, go to the **Reasoning **tab. ::: :::WorkflowBlockItem Adjust your agent's settings, tools, or knowledge based on what you discover. ::: :::: You've now viewed scenario run details to understand how to resolve errors in your agent. Once you've tested your agent, it's now ready to use in your scenarios. ::::: :::::ExpandableHeading ## Manage your AI agent (optional) Optionally, once you've created and tested your agent, you can duplicate or delete it. Duplicate an agent to use it again in a scenario. You can do this by cloning or copying it: - Clone to duplicate only the **Make AI Agent (New)** > **Run an agent** module - Copy to duplicate the **Make AI Agent (New)** > **Run an agent **module and its tools ### Clone your AI agent To clone an agent: ::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, right-click the **Make AI Agent (New)** > **Run an agent **module. ::: :::WorkflowBlockItem Click **Clone**. ::: :::WorkflowBlockItem Link the cloned **Run an agent **module to the scenario. ::: :::WorkflowBlockItem Click the module and adjust any of its settings. ::: :::WorkflowBlockItem Click **Save **on the Scenario toolbar. ::: :::: You've now cloned your agent. ### Copy your AI agent and its tools To copy an AI agent and its tools: ::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, press the `Shift` key while clicking the canvas. ::: :::WorkflowBlockItem Drag over the **Make AI Agent (New)** > **Run an agent **module and its tools. ::: :::WorkflowBlockItem Press `Ctrl` + `C` if you have Windows, or `Command` + `C` if you have a Mac. ::: :::WorkflowBlockItem Click the canvas. ::: :::WorkflowBlockItem Press `Ctrl` + `V` if you have Windows, or `Command` + `V` if you have a Mac. ::: :::WorkflowBlockItem Link the copied **Run an agent **module and tools to the scenario. ::: :::WorkflowBlockItem Click the **Run an agent** module and its tools, and adjust any of their settings. ::: :::WorkflowBlockItem Click **Save **on the Scenario toolbar. ::: :::: You've now copied your agent. ### Delete your AI agent You have two ways to delete your agent: by deleting the **Make AI Agent (New)** > **Run an agent** module, or by deleting the scenario. To delete the **Run an agent **module: ::::WorkflowBlock :::WorkflowBlockItem In the Scenario Builder, right-click the **Make AI Agent (New)** > **Run an agent** module. ::: :::WorkflowBlockItem Click **Delete module**. ::: :::: You've now deleted the **Make AI Agent (New)** > **Run an agent** module. To add a new one, right-click and select **Add a module**. To delete a scenario: ::::WorkflowBlock :::WorkflowBlockItem Click **Scenarios **on the left sidebar. ::: :::WorkflowBlockItem In the scenario list, find the AI agent scenario you want to delete. ::: :::WorkflowBlockItem Click the three-dot menu next to the scenario. ::: :::WorkflowBlockItem Click **Delete**. ::: :::: You've now deleted the scenario. ::::: Next, to walk through a guided use case, see [Sales outreach AI agent use case](docId\:eG7rWQ8eRecFa8XngZtLZ).