Skip to main content
Discover how to connect Engini with Agent.ai and use its activities to search, inspect, and run AI agents directly from Engini workflows. Agent.ai is a platform for discovering, building, and running AI agents. With the Agent.ai connector in Engini, you can search for available agents, retrieve agent metadata, run selected agents with dynamic input properties, and send custom authorized API requests when needed.

Getting Started with Agent.ai

Prerequisites

Before connecting Agent.ai to Engini, make sure you have:
  1. An Agent.ai account.
  2. An Agent.ai API key.
  3. Access to your Engini account.

Retrieve your Agent.ai API Key

  1. Log in to your Agent.ai account.
  2. Open the Connections in your Agent.ai account.
  3. Inside connections navigate to API page.
  4. Copy your API key.
Keep this key secure. It provides access to your Agent.ai account and usage, so it should be treated like a password.

Connecting Engini to Agent.ai

Enter your Engini account at https://app.engini.io.
  1. Navigate to Connections page by clicking on the Connections on the left sidebar or by clicking here.
  2. Click on the “New Integration” option located at the topbar.
  3. Choose Agent.ai option from the available applications.
  4. Enter the following details in the New Integration form and press Save: 1. Connection name - Enter a meaningful name that will help you identify the connection later. 2. Api Key - Enter your Agent.ai API key. The hint “Your Agent.ai API key” appears below the field. This key is used to authenticate requests made through the Agent.ai connector. 3. Save - Click the Save button to save the connection.

Actions

Get Agents

Searches for Agent.ai agents according to the selected search criteria. Agent.ai - Get Agents action
  1. Status - Text field that defaults to public. Keep it, or replace it with another agent status, or map it from a previous step, to choose which agents are returned. For example, public, private, team, or all.
  2. Top N - Enter the maximum number of agents Engini will return. Leave it empty to return all agents.
  3. Add Filter - Click Add Filter to define conditions that narrow down the data list and return only the relevant items. To learn more about using filters, click here.

Get Agent

Retrieves detailed information about a specific Agent.ai agent.
  1. Status - Select the agent status you want to filter by, to find the agent. The selected value appears as a blue tag. For example, public, private, team, or all.
  2. Agent Id - Select the agent you want to retrieve, or map its Id from a previous step. This field becomes available after you select a Status. Click the field to see the agents that match that status and pick one; the selected agent appears as a blue tag.

Run Agent

Runs a selected Agent.ai agent from inside an Engini workflow.
  1. Status - Select the agent status you want to filter by. The selected value appears as a blue tag. For example, public, private, team, or all.
  2. Agent Id - Select the agent you want to run, or map its Id from a previous step. This field becomes available only after you select a Status. Click the field to see the agents that match that status and pick one; the selected agent appears as a blue tag.
Note: You must enter an Agent Id before entering the Properties field.
  1. Properties – Enter the full JSON object required by the selected agent. This field should be filled only after entering an Agent Id. The required JSON structure depends on the selected Agent.ai agent. Each agent may require different fields according to its own input schema. For example: {"company": "Acme Ltd", "topic": "pricing"}.

Save To File

Save text content as a file in the selected format. Specify the file type, provide the content you want to save, and enter a file name. The action generates the file, which can then be used in later workflow steps, such as sending it by email, uploading it to cloud storage, or sharing it with other applications.
  1. File Type – Enter the file format you want to create, or pick one from the list of options. The default is pdf. Other options: docx, html, md, odt, tex, azw3, epub, or png.
  2. Body – Enter the content that will be saved inside the file. This can be plain text, Markdown, HTML, or any supported content structure according to the selected file type.
  3. File Name – Enter the output variable name that will store the generated file URL. For example: saved_file.
Note: After the action runs, Agent.ai returns the generated file URL under this name.

Send API Request

Sends a custom API request to Agent.ai by specifying the endpoint, HTTP method, headers, and query parameters.
  1. Base URL - The main endpoint of the API you want to call (e.g., the server or service URL).
  2. Relative URL The specific path or resource you want to access, appended to the Base URL.
  3. Method - Defines the HTTP method used for the request (e.g., GET, POST, PUT, DELETE).
  4. Body Type - Specifies the format of the request body (e.g., JSON, form-data).
    • application/json – Sends the request body in JSON format. Commonly used by REST APIs.
    • Custom (use Content-Type header) – Allows you to define a custom body format by manually setting the Content-Type header.
    • application/x-www-form-urlencoded – Sends the body as URL-encoded key-value pairs, commonly used in form submissions.
    • file – Sends a file as the request body.
    • multipart/form-data – Sends form data that may include both text fields and files.
    • text/html – Sends the request body as HTML content.
    • text/plain – Sends the request body as plain text.
    • text/xml – Sends the request body in XML format.
  5. Body - The payload sent with the request, usually required for methods like POST or PUT.
  6. Add Headers - Allows you to include additional headers (e.g., Authorization, Content-Type) required by the API.
  7. Add Queries - Allows you to add query parameters to the request URL (e.g., filters, pagination).