CUSTOMER SUPPORT
Real-Time Angry-Escalation Pager for On-Call Leads
Listens for new Zendesk escalations as they happen, uses an LLM to flag the genuinely furious or high-revenue ones.
How it runs
The automated pipeline, trigger to output.
- TriggerZendesk escalation webhookZendesk
- ActionClassify tone, severity, account tierOpenAI
- LogicBranch: page-worthy vs routine
- ActionOpen PagerDuty incident for severe casesPagerDuty
- OutputPost context heads-up to support channelMicrosoft Teams
What it does
Catches escalations the moment they happen instead of at the next standup, judges whether each one is actually severe (not just reflexively escalated), and wakes up the right person only when it matters.
When to use it
Use it when a slow standup-only summary lets a furious enterprise customer stew for hours. Ideal for teams with a PagerDuty on-call rotation who want signal, not a firehose of every escalation.
How it works
- 1A Zendesk webhook fires on every ticket escalation event.
- 2An OpenAI step classifies tone and severity, weighing language intensity and account tier into a single 'page-worthy' verdict with a reason.
- 3A logic branch checks the verdict: page-worthy escalations continue, routine ones are silently logged and stop.
- 4For page-worthy tickets, a PagerDuty incident is created with the customer name, sentiment reason, and ticket link.
- 5A parallel Teams message posts a quieter heads-up to the support channel so the wider team has context when they wake up.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PagerDutyIncidents, on-call, escalations.
- 4Connect Microsoft TeamsChannels, chats, files.
- 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
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.