CUSTOMER SUPPORT
Detect inbound language in Front and route to the regional team with a translated summary
When a new conversation lands in a shared Front inbox, detect its language and, if it isn't English, reassign it to the matching regional team and post a translated summary…
How it runs
The automated pipeline, trigger to output.
- TriggerNew inbound conversation in shared Front inboxFront
- ActionClassify message language with OpenAIOpenAI
- LogicBranch: English vs non-English
- ActionSummarize and translate request to EnglishOpenAI
- ActionReassign conversation to regional team inboxFront
- OutputPost translated summary as internal commentFront
What it does
Non-English emails sitting in an English-first shared inbox wait while someone figures out who can read them. This template reads each new Front conversation, classifies the language, and if it isn't English, moves the conversation to the correct regional team inbox and drops a concise English summary plus key details as an internal comment.
When to use it
Use it when one Front inbox receives mail in several languages and you have dedicated regional teams (for example DE, FR, ES, JP) who should own those conversations. It removes the manual triage step and the back-and-forth of asking colleagues to translate.
How it works
- 1A new inbound conversation in the watched Front inbox fires the trigger.
- 2OpenAI classifies the body's primary language and returns an ISO code.
- 3A branch checks whether the language is English; English conversations pass through untouched.
- 4For non-English mail, OpenAI produces a short English summary of the customer's request.
- 5Front reassigns the conversation to the inbox or teammate mapped to that language.
- 6Front posts the translated summary and detected language as an internal comment for the receiving agent.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Customer Support workflows
Send a tailored Loom onboarding sequence on Front first-reply
When a new customer's first email lands in Front, this picks the Loom onboarding walkthroughs matching their plan and use case, builds a friendly sequenced reply.
Suggest the right Loom video by classifying Intercom message intent
Reads each new inbound Intercom conversation, classifies what the customer is trying to do, and surfaces the best-matching Loom walkthrough to the agent as an internal note.
Draft personalized fix-live replies for support to review
When a Sentry issue resolves, an agent reads each linked ticket's full thread and drafts a tailored 'your fix is live' reply per requester.
Close the loop with requesters when a Linear bug moves to Done
When a Linear issue created from a support escalation moves to Done after deploy, look up the originating Zendesk tickets and notify each requester that their reported bug is…
Reopen and notify Front conversations when their bug fix deploys
When a deploy resolves a Sentry issue, find the snoozed or closed Front conversations linked to it, reopen them, and send the customer a reply that the fix is now live.
Tell Intercom users their reported bug shipped after a Vercel deploy
On a successful Vercel production deployment, match the release's resolved Sentry issues to Intercom conversations and message each affected user that their reported issue is…
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.