Automation · Customer service and scheduling
Serve customers who write in another language on WhatsApp with your business glossary in DeepL
An AI agent replies on WhatsApp in the customer's language, translating with DeepL and with your product glossary.
How do I serve tourists who write in English on WhatsApp without changing my product names?
When a customer writes in English, French or Portuguese, the Met builds the reply with your business information and translates it with DeepL into the customer's language. First it checks that DeepL translates into that language, finds your business glossary for that language pair and the style rule you defined, and translates with both. That way "Tour Cafetero Premium" or "Habitación Doble Superior" come out the same in every message and the tone is the one you chose. If DeepL does not translate into that language, the Met replies in Spanish and says so.
What starts it
When the customer writes
It starts when a customer writes on WhatsApp in another language. There is no trigger to configure: the Met assigned to the line translates inside that conversation.
Nothing to set up. The Met assigned to that channel picks up the conversation and runs the procedure inside it.
Who runs it
Support Met that replies in the customer's language
Customer service team
This is not a named, seeded Met. It is the Met that already answers the business's WhatsApp, with DeepL connected: its work ends when the customer gets the reply in their language with your glossary's terminology.
Run by the customer support Met
Channels: WhatsApp
What you need connected
- DeepL Sell and serve
5 steps · 5 tools
The procedure, step by step
Each step shows the tool that runs. They belong to the real connector: if one of them stopped existing, this page would not build.
- 1
Confirm DeepL translates into that language
The Met checks DeepL's list of target languages. If the customer's language is not there, it replies in Spanish and says so, instead of sending a translation DeepL does not make.
- 2
Find the business glossary
The Met lists the glossaries in your DeepL account and keeps your business's one. Glossaries store your product and service names for each language pair.
- 3
Check the terms for the language pair
The Met brings the glossary dictionary terms from Spanish into the customer's language. If that pair does not exist in the glossary, it translates without it and your team can add it later in DeepL.
- 4
Find the style rule
If your team defined a style rule in DeepL, such as a friendly tone or phrases that are not used, the Met finds it to apply it in the translation.
- 5
Translate and reply
The Met translates its reply from Spanish into the customer's language with the glossary, the style rule and the formality level, stating Spanish as the source language, and sends it on WhatsApp.
Before you start
What you need ready
The Met solves none of these for you. If one is missing, the automation stops there.
-
DeepL connected in Met
In Met, open Connections → DeepL → Connect and sign in with your business's DeepL account.
-
A glossary with your product names
Create a glossary in DeepL with your product and service names for each language you serve. Without a glossary, translation works, but names may vary.
-
A WhatsApp line with the Met assigned
The business connects its WhatsApp Business API line and assigns the Met that serves customers. Translation happens inside that conversation.
The limits
What this automation does NOT solve
Better said here than discovered halfway through the rollout.
-
It does not translate files the customer sends. This procedure translates text messages; documents are not in the listing.
-
It does not create the glossary. If a term is missing, the Met does not make it up: your team adds it in DeepL and it is used from there.
-
It does not know your business through DeepL. The reply comes from the information the Met already has; DeepL only carries it into the other language.
-
It does not serve languages DeepL does not translate. In that case the Met replies in Spanish and says so.
FAQ
Questions about this automation
The reply arrives in their language, with your glossary's product names and the tone you chose. If you want to say so explicitly, put it in the Met's instructions.
DeepL detects a text's language when it is not given. The Met replies in the main language of the customer's message.
A DeepL glossary stores dictionaries per language pair. You need the Spanish to customer language pair for each language you serve.
Keep going
Other automations built on the same tools
Customer service and scheduling
Open a Linear issue from a customer report on WhatsApp and tell them how it is going
How do I make customer reports on WhatsApp arrive in Linear as issues?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 6 real tools
- Needs:
- Linear
Customer service and scheduling
Open a Freshdesk ticket from WhatsApp and tell where it stands
How do I turn a complaint that arrives on WhatsApp into a Freshdesk ticket without copying it by hand?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 10 real tools
- Needs:
- Freshdesk
Customer service and scheduling
Open a Gorgias ticket from WhatsApp and escalate it to the team that solves it
How do I move a complaint that arrives on WhatsApp into Gorgias without copying it by hand or losing what the customer said?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 7 real tools
- Needs:
- Gorgias
Customer service and scheduling
Open a Jira issue from a report that comes in on WhatsApp and answer how it is going
How do I make customer reports on WhatsApp arrive in Jira as issues?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 6 real tools
- Needs:
- Jira y Confluence
Want this automation running on your own data?
We will show it to you with your accounts connected, not with a canned demo.