CUSTOMER SUPPORT
Agent that triages Intercom tickets and files confirmed bugs to Linear
A Paperclip agent reads each Intercom conversation, tags it, suggests a macro for routine issues.
How it runs
The automated pipeline, trigger to output.
- TriggerNew or updated Intercom conversationIntercom
- ActionAgent reads thread and classifies request vs bugOpenAI
- LogicBranch: routine request or confirmed bug
- ActionTag and suggest macro in Intercom (routine path)Intercom
- ActionCreate structured Linear issue (bug path)Linear
- OutputLink Linear issue back to Intercom and notify SlackSlack
What it does
This agentic workflow goes beyond tagging. For routine questions it tags the Intercom conversation and recommends a macro. When it determines the report is an actual product bug, it extracts reproduction steps, severity, and affected area, opens a structured Linear issue, and links that issue back into the Intercom conversation so support and engineering stay connected.
When to use it
Use this when support is the front door for bug reports and handoffs to engineering are inconsistent or lossy. It keeps triage and escalation in one motion so customers get acknowledged and engineers get an actionable ticket.
How it works
- 1A new or updated Intercom conversation triggers the agent.
- 2The agent reads the thread and decides whether it is a routine request or a bug.
- 3A logic branch splits routine versus bug handling.
- 4For routine items, an action tags the conversation and suggests a macro in Intercom.
- 5For bugs, an action creates a Linear issue with extracted repro steps and severity.
- 6The output posts the Linear link back onto the Intercom conversation and notifies the team in Slack.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect LinearIssues, projects, cycles, triage.
- 3Connect OpenAIModels, embeddings, files.
- 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.