TICKET MANAGEMENT
Agent-Driven ARR Triage and Reply Drafting for Intercom
On a new Intercom conversation, an agent looks up the account's ARR and history, decides a severity tier and routing, drafts a tier-appropriate first reply.
How it runs
The automated pipeline, trigger to output.
- TriggerNew Intercom conversationIntercom
- ActionGather account ARR and conversation historyIntercom
- LogicAgent reasons over impact to set severity and team
- ActionApply tier and draft first reply in IntercomIntercom
- OutputLog decision and rationale to NotionNotion
What it does
This is the reasoning-heavy version of revenue-weighted triage. Instead of a fixed formula, an agent reads the new Intercom conversation, gathers the account's ARR and recent ticket history, judges true business impact, picks a severity and team, and drafts a first response whose tone and urgency match the account's value.
When to use it
Choose this when impact is too nuanced for thresholds alone — a small account hitting a billing outage may matter more than a big account asking a how-to. It fits teams who want a human-reviewable recommendation rather than a silent auto-action.
How it works
- 1A new Intercom conversation triggers the agent with the contact and message body.
- 2The agent retrieves the account's ARR and recent conversation history to understand context and trend.
- 3It reasons over revenue, sentiment, and impact to assign a severity tier and the right team.
- 4It applies the tier and assignment back to the Intercom conversation and drafts a matching first reply for an agent to approve.
- 5It logs the decision, ARR, and rationale to a Notion triage register for audit and tuning.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect NotionPages, databases, comments.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Ticket Management workflows
Enrich Discord bug reports with Sentry errors before filing in Linear
Takes a Discord bug report, has an LLM pull out likely error signatures, searches Sentry for matching events.
Front-to-Linear Recurring Bug Linker
When a Front ticket is tagged as a bug, it searches Linear for an existing matching issue and either links the ticket to that parent issue or opens a new tracked one.
Front Duplicate Conversation Clusterer
When a new Front conversation arrives, it semantically compares the report against open conversations.
Intercom Known-Issue Auto-Responder
When a new Intercom conversation matches a known active incident, it attaches the conversation to that incident's parent ticket and sends the customer the current status reply.
Weekly reopen-by-agent coaching digest
Aggregates each agent's solved-then-reopened tickets for the week, identifies the most common reopen reason per agent, and emails a private coaching digest to the support manager.
Escalate repeat reopens to a Linear bug
Detects when the same underlying issue reopens across multiple tickets, uses an AI agent to cluster them by root cause.
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.