AI-powered customer conversation management software.
AI-powered customer conversation management software. On Nagent, Respond.io is exposed as a fully-configurable customer support integration that any agent can call — 7 actions, and API key authentication. No code is required to wire Respond.io into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Respond.io to automate the kinds of tasks customer support teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Respond.io into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Respond.io, with input parameters and output schema. Drop these into any step of an agent built in Helix.
RESPOND_IO_CREATE_COMMENTTool to add a comment (internal note) to a contact's conversation. Use after verifying the contact identifier.
Input parameters
Content of the comment (internal note), up to 1000 characters. You can mention other users using `{{@user.ID}}`.
Identifier of the contact; either 'id:<contact_id>', 'email:<email>' or 'phone:<E.164_phone>'. Example: 'id:123', 'email:abdc@gmail.com', 'phone:+60121233112'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RESPOND_IO_CREATE_CONTACTCreates a new contact in the respond.io workspace with the specified details. The contact is identified by email, phone number, or contact ID. Supports adding profile information, language preferences, and custom fields that have been pre-configured in the workspace.
Input parameters
Email address of the contact
Phone number of the contact including country code
ISO 639-1 two-letter language code (e.g., 'en' for English, 'es' for Spanish)
Last name of the contact
First name of the contact
Unique identifier for the contact in one of these formats: 'email:<email_address>' (e.g., 'email:john@example.com'), 'phone:<phone_number>' (e.g., 'phone:+60121233112' with country code), or an existing contact ID
URL of the contact's profile picture
ISO 3166-1 alpha-2 two-letter country code (e.g., 'US' for United States, 'MY' for Malaysia)
List of custom fields for the contact. Note: Custom fields must already exist in the workspace before they can be assigned to a contact
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RESPOND_IO_CREATE_SPACE_TAGCreates a new tag in the Respond.io workspace for organizing and categorizing contacts and conversations. Tags help with segmentation, filtering, and workflow automation. Each tag must have a unique name within the workspace.
Input parameters
Name of the tag. Must be unique within the workspace. Cannot contain emojis or certain invalid characters. Supports spaces, letters, numbers, and common special characters like !@#$%.
(Optional) Hexadecimal color code for visual identification of the tag in the UI, e.g., '#FF5733'. Note: Currently the API may reject this parameter with validation errors.
(Optional) Brief text describing the tag's purpose or usage. Helps team members understand when to apply this tag.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RESPOND_IO_GET_MESSAGETool to retrieve a specific message. Use when you need the details of a message sent to or received from a contact.
Input parameters
Unique ID of the message to retrieve.
Identifier of the contact, can be a phone number ('+60121233112'), email ('abdc@gmail.com'), or contact ID prefixed by 'id:' (e.g., 'id:123').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RESPOND_IO_LIST_CHANNELSTool to retrieve a list of channels connected to the workspace. Use when you need to enumerate all messaging channels with pagination support.
Input parameters
Number of items to return (page size). Default is 10, maximum 100.
Pointer to the channel ID from where the next batch of records should start.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RESPOND_IO_LIST_USERSTool to retrieve a list of users in the workspace. Use when you need to fetch all workspace users for auditing or assignment.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RESPOND_IO_UPDATE_SPACE_TAGUpdates an existing workspace tag by its current name. You can modify the tag's name, description, or emoji. Note: Color codes are not currently supported by the API and will be rejected if provided. At least one field besides currentName must be provided to update.
Input parameters
New name for the tag (if you want to rename it)
Emoji to associate with the tag (single emoji character)
Hex color code for the tag (Note: Currently not supported by API and will return error if provided)
The current name of the tag you want to update (must match exactly)
New description for the tag (updates or sets the description)
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 62 agents privately built on Nagent that already use Respond.io.
Build on Nagent
Connect Respond.io to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Respond.io, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Respond.io is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Respond.io is connected, you configure its 7 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Respond.io steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Respond.io event fires, the agent kicks off automatically.
Every Respond.io action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Respond.io ships with 7 pre-built customer support actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Respond.io together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Respond.io-based workflows tailored to your business.