CUSTOMER SUPPORT
Summarize repeated Intercom conversations into a draft macro and article
Groups recent Intercom conversations by recurring intent, and for the most common topics with no canned reply.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule fires
- ActionFetch recent Intercom conversationsIntercom
- ActionGroup by recurring intent and rankOpenAI
- LogicKeep high-volume intents lacking a saved reply
- ActionDraft article and saved-reply textOpenAI
- ActionSave article draft to NotionNotion
- OutputPost saved-reply suggestion to SlackSlack
What it does
It mines your Intercom inbox for the questions agents type fresh answers to over and over, then produces both a public help article and an internal saved-reply draft so the next agent answers in one click.
When to use it
Use it when your Intercom team is re-typing similar answers and your saved replies and help center have not kept pace with what customers actually ask.
How it works
- 1A daily schedule starts the run.
- 2It pulls recent closed Intercom conversations and extracts the customer's intent from each.
- 3An LLM groups conversations by recurring intent and ranks them by volume.
- 4A filter keeps only high-volume intents that lack an existing saved reply.
- 5For each kept intent, an LLM drafts a customer-facing help article and a concise internal saved-reply, both built from the agents' best historical responses.
- 6The article draft is saved to a Notion review database and the saved-reply suggestion is posted to the team's Slack for quick adoption.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect NotionPages, databases, comments.
- 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.