CUSTOMER SUPPORT
Weekly Intercom Macro Miner: Cluster Resolved Threads into Draft Canned Replies
Every week, pulls resolved Intercom conversations, clusters them by topic, and drafts a candidate macro for each recurring pattern so support leads can approve high-value canned…
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionFetch resolved Intercom conversations from the last 7 daysIntercom
- ActionEmbed and cluster threads by topicHugging Face
- LogicKeep only clusters above the minimum recurrence threshold
- ActionDraft a macro title and reply body per clusterHugging Face
- OutputPost draft macros to the Notion review boardNotion
What it does
Once a week this workflow harvests all conversations Intercom closed since the last run, groups them by what the customer was actually asking, and writes one suggested macro per recurring topic. Each suggestion includes a proposed title, the canned reply text drawn from how agents really resolved the thread, and how many conversations it would have covered. The drafts land in a Notion review board so a lead can approve, edit, or reject before anything becomes a real saved reply.
When to use it
Use it when your team answers the same questions over and over but nobody has time to formalize macros. It turns the backlog of resolved tickets into a ranked list of the replies worth canning.
How it works
- 1A weekly schedule fires the run.
- 2Fetch all Intercom conversations marked resolved in the past 7 days, including the agent reply that closed each one.
- 3Embed every thread and cluster them by semantic similarity using a Hugging Face model.
- 4Drop clusters below a minimum size so only recurring patterns survive.
- 5For each surviving cluster, synthesize a draft macro title and reply body plus the coverage count.
- 6Post each draft as a card to a Notion review database for human approval.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Connect NotionPages, databases, comments.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Customer Support workflows
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.
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.
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.
Article Volume-Rebound Early Warning (Datadog)
Streams support ticket-tag events into Datadog, watches for topics whose volume is reaccelerating against a decaying article.
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.