CUSTOMER SUPPORT
Log Front inbound-language mix to Postgres and report the daily breakdown
On a daily schedule, pulls the previous day's Front conversations, detects each one's language, writes the counts to Postgres.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule after business hours
- ActionFetch previous day's Front conversationsFront
- ActionDetect language per conversation with OpenAIOpenAI
- LogicAggregate counts per language
- ActionUpsert daily counts into PostgresPostgres
- OutputPost language-mix digest to SlackSlack
What it does
Staffing decisions for multilingual support usually run on guesswork. This template turns the guesswork into data: each day it reviews the prior day's inbound Front conversations, detects the language of each, records per-language counts in a Postgres table, and posts a digest to Slack showing the inbound mix and any new languages seen.
When to use it
Use it when you need a defensible record of which languages your inbox actually receives, to plan hiring, set SLAs by region, or justify a new regional team. The Postgres history lets you track trends over weeks rather than reacting to single conversations.
How it works
- 1A daily schedule trigger fires after the close of business.
- 2Front returns all inbound conversations from the previous day.
- 3OpenAI detects the language of each conversation in a batch and returns codes.
- 4Counts are aggregated per language and upserted into a Postgres metrics table keyed by date.
- 5A Slack message posts the day's language breakdown, highlighting any language not seen before.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Customer Support workflows
Flag Live Intercom Chats With No Help Article and Alert Slack
When an Intercom conversation closes, checks whether the customer's question is already covered by a help article.
Negative VIP CSAT to Owner Callback Scheduler
When a VIP submits a low Intercom CSAT rating, drafts a recovery note with an LLM and books a callback on the account owner's Google Calendar within their working hours.
CEO Agent: Mine Last Month's Tickets and Publish a Deflection Plan
Monthly, an agent investigates the top recurring Zendesk ticket themes, drafts and publishes the highest-confidence help articles to ReadMe.
Mine a Discord Support Channel for Recurring Questions to Document
On a daily schedule, scans a Discord support channel for questions the community keeps asking, deduplicates against existing ReadMe docs.
Daily VIP Sentiment Digest for Account Owners
Each morning, pulls the prior day's Intercom conversations for VIP accounts, summarizes the overall mood per account with an LLM.
VIP Reply Sentiment Watcher with Account-Owner Escalation
Scores every inbound Intercom reply from a VIP customer for frustration and, when it crosses the anger threshold, pings the account owner in Slack with the conversation link…
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.