Intercom Multilingual Auto-Reply
When an Intercom conversation starts in a non-English language, the flow detects the language with Microsoft Translator, adds an English translation as an internal note for the agent, and sends the customer an acknowledgement translated into their own language. Lets a single-language team support a global Intercom audience instantly.
Provided as-is, without warranty of any kind. Review and test each pattern in a non-production environment before deploying it to live automations. See our Terms.
Overview
This flow removes the language barrier from Intercom using Microsoft Translator. When a new conversation is created in a non-English language, the flow detects the language, posts an English translation as an internal admin note for the agent, and replies to the customer with an acknowledgement translated into their own language. It also emails the support mailbox a summary.
Why it matters: A single-language support team can't respond instantly to a global chat audience. Detect -> translate-in -> acknowledge-out gives immediate, localized responses while agents continue to work in English. Ships Off; going live requires only authorizing the connections and setting the environment-variable values.
Use Case
A support team receives Intercom chats in many languages. They want (1) an instant localized acknowledgement to the customer, (2) an English rendering of the message for the agent, and (3) a heads-up email so the right person can pick the conversation up.
Flow Architecture
When a new conversation is created
Intercom TrigNewConversationFires per new conversation (3-min poll, splitOn).
Initialize variables (x10)
Initialize VariableAgent language, ack template, Intercom + Translator config, notify email.
Compose Plain Message
ComposeStrip common HTML tags from the first customer message.
Detect Language
HTTP POST Translator /detectIdentify the source language (connector has no Detect op).
Condition Non English
Condition (If)Proceed only when detected language != agent language.
Translate To English
Translator TranslateCustomer message -> agent language.
Add Internal Note
HTTP POST /conversations/{id}/reply (note)Post English translation onto the conversation.
Translate Ack
Translator TranslateEnglish acknowledgement -> customer's language.
Send Localized Ack
HTTP POST /conversations/{id}/reply (comment)Public reply to the customer in their language.
Notify Agent
Office 365 Outlook SendEmailV2Email the support mailbox a summary.
Environment Variables
| Schema name | Type | Default | Description |
|---|---|---|---|
| flowlibs_AckTemplateEnglish | String | Thank you for reaching out - a support agent will reply shortly. | Base English acknowledgement, translated before sending. |
| flowlibs_AgentLanguage | String | en | Support team's working language; other languages trigger the translate path. |
| flowlibs_NotificationEmail | String | alerts@yourcompany.com | Mailbox that receives the agent summary email. |
| flowlibs_IntercomApiBase | String | https://api.intercom.io | Intercom REST base URL. |
| flowlibs_IntercomApiToken | String | REPLACE_WITH_INTERCOM_TOKEN | Intercom Bearer token for the note + reply calls. |
| flowlibs_IntercomVersion | String | 2.11 | Intercom-Version header value. |
| flowlibs_IntercomAdminId | String | (configure) | Admin id that authors the note + reply. |
| flowlibs_TranslatorTextEndpoint | String | https://api.cognitive.microsofttranslator.com | Translator endpoint for the HTTP detect call. |
| flowlibs_TranslatorTextKey | String | REPLACE_WITH_TRANSLATOR_KEY |
Connectors & Connections
| Connector | API name | Actions used |
|---|---|---|
| Intercom | shared_intercom | TrigNewConversation POST /conversations/{id}/reply |
| Microsoft Translator | shared_microsofttranslatorv | Translate |
| Office 365 Outlook | shared_office365 | SendEmailV2 |
Note — All connections are referenced as solution connection references; the flow is portable between environments as long as a connection is mapped at import time.
Customization Guide
Almost every realistic variant of this flow can be implemented by changing environment variable values. A few cases require small edits inside the flow definition — those are called out explicitly below.
- Detection threshold
- To skip very short messages (emoji-only, hi), add a length check on Compose Plain Message before Detect Language.
- Reply translation on send
- Extend the pattern to translate the agent's English reply back into the customer's language when they respond.
- Language tag / routing
- Add an Intercom HTTP /conversations/{id}/tags call to tag the conversation with the detected language for routing.
- Skip known-English locales
- Bypass the translate path for users whose Intercom locale is already English.
- Public vs. private reply
- The customer acknowledgement uses message_type comment; switch to note if you want it agent-only.
Key Expressions
The flow is intentionally light on Power Fx / WDL gymnastics — the heaviest expressions are the branch-name concatenation and the approval outcome check. They are listed below in the order they appear in the flow.
EXPR.01Detected language (HTTP detect)
Read the detected language code.
EXPR.02Detected language with fallback
Fallback to the agent language.
EXPR.03Non-English gate
Only translate non-agent-language chats.
EXPR.04Translated text (Translator V3)
Extract the translated text.
EXPR.05Intercom reply URL
Build the reply endpoint URL.
Customize & download
Generate a ready-to-import copy of this solution with your environment-variable values baked in — available on Base, Pro, or Team.
Upgrade to customize
Comments
Sign in to join the conversation.
Sign inNo comments yet. Be the first to share your experience with this flow.