CUSTOMER SUPPORT
Weekly VoC theme miner: cluster Intercom transcripts into Linear epics
Every week, pull resolved Intercom conversations, cluster them into product-feedback themes with an LLM.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionFetch last week's resolved Intercom conversationsIntercom
- ActionCluster transcripts into named themes (OpenAI)OpenAI
- LogicDrop themes below minimum volume threshold
- ActionUpsert a Linear epic per theme with quotesLinear
- OutputPost top-themes digest to the teamLinear
What it does
Turns a week of support chatter into a ranked list of product-feedback epics. It reads resolved Intercom conversations, groups them into recurring themes (billing confusion, missing export, onboarding drop-off, etc.), and writes each theme to Linear as an epic with a count, trend, and verbatim customer quotes so product can prioritize from evidence instead of anecdotes.
When to use it
Run it when your support volume is too high to read every ticket but product keeps asking "what are people actually complaining about?" Ideal for weekly triage or sprint-planning prep.
How it works
- 1A weekly schedule fires the run.
- 2Pull all Intercom conversations closed in the last 7 days, including transcript text and tags.
- 3An OpenAI step embeds and clusters the conversations into named themes, each with a one-line summary and 2-3 representative quotes.
- 4A logic step filters out themes below a minimum conversation count to suppress noise.
- 5For each surviving theme, upsert a Linear epic: create it if new, or append the week's count and quotes if it already exists.
- 6Output a digest of the top themes to the team.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LinearIssues, projects, cycles, triage.
- 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.