CUSTOMER SUPPORT
Feature-request miner that links Intercom themes to HubSpot revenue
Daily, extract feature requests from Intercom conversations, dedupe them into canonical themes.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule fires
- ActionFetch day's Intercom conversations with requester infoIntercom
- ActionExtract and dedupe feature requests into themes (OpenAI)OpenAI
- ActionMatch requesters to HubSpot companies and ARRHubSpot
- LogicAggregate revenue and count per theme
- OutputPost revenue-weighted theme rankingSlack
What it does
Finds feature requests buried in support conversations and answers the question product really cares about: how much money is asking for this? It pulls Intercom conversations, extracts and de-duplicates requests into canonical themes, matches each requester to their HubSpot company, and sums the associated deal or ARR value per theme.
When to use it
Use it when feature prioritization keeps devolving into whoever-shouted-loudest. This gives a revenue-weighted backlog: each theme ranked by the total account value behind it.
How it works
- 1A daily schedule fires the run.
- 2Pull the day's Intercom conversations with the requester's email and company.
- 3An OpenAI step extracts explicit feature requests and maps each to a canonical theme, merging paraphrases.
- 4For each requester, look up the matching HubSpot company and its deal/ARR value.
- 5A logic step aggregates revenue and request count per theme.
- 6Output the revenue-weighted theme ranking to a shared sheet and the product channel.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect HubSpotCRM, deals, marketing, support.
- 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.