CUSTOMER SUPPORT
Detect Repeated Unanswered Zendesk Tickets and Open a Confluence Doc Task
Scans recent Zendesk tickets weekly, clusters questions that agents could not answer from existing docs.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionPull last 7 days of Zendesk ticketsZendesk
- LogicNormalize and cluster questions with LLMOpenAI
- ActionSearch Confluence for existing coverageConfluence
- LogicKeep clusters with 5+ tickets and no doc
- ActionOpen a ClickUp doc-writing task per gapClickUp
- OutputPost gap summary to SlackSlack
What it does
Finds the questions your support team keeps getting asked but has no documentation for, then turns each recurring gap into a concrete writing task — so the same question stops eating agent time.
When to use it
Run this when ticket volume is high enough that agents are answering the same things from memory and your knowledge base is falling behind. Best for teams with a Confluence KB and ClickUp for doc work.
How it works
- 1A weekly schedule fires the run.
- 2Pull the last 7 days of solved and pending Zendesk tickets, including the question text and any internal notes.
- 3Use an LLM to normalize each ticket into a canonical question and cluster near-duplicates together.
- 4For each cluster, search Confluence for an existing article that answers it.
- 5Filter to clusters that appear 5+ times AND have no matching Confluence page — these are the real gaps.
- 6Create one ClickUp task per gap with the question, ticket count, and example ticket links.
- 7Post a summary of the new gaps to the support Slack channel.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ConfluenceSpaces, pages, blueprints.
- 4Connect ClickUpDocs + tasks + chats in one workspace.
- 5Connect SlackChannels, DMs, threads, mentions.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, 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.