CUSTOMER SUPPORT
KB Gap Miner: Cluster Unmatched Tickets and Draft Missing Articles
Weekly, it scans closed Zendesk tickets that never linked to a help-center article, clusters them by theme, drafts a new article for each gap.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionFetch solved Zendesk tickets from the past weekZendesk
- LogicKeep only tickets with no linked KB article
- ActionCluster unmatched tickets into article topicsOpenAI
- ActionDraft an article per cluster grounded in ticket textOpenAI
- ActionCreate unpublished draft page in ConfluenceConfluence
- OutputPost drafts to SME review channel in SlackSlack
What it does
Most support backlogs hide the same unanswered questions over and over. This workflow finds the tickets your knowledge base could not answer, groups them into real article topics, and produces a first draft so an SME only has to review instead of write from scratch.
When to use it
Run it when your KB feels stale, deflection is low, or agents keep copy-pasting bespoke answers. It is built for teams who want continuous KB coverage without a manual content audit.
How it works
- 1A weekly schedule fires the run.
- 2It pulls the past week's solved Zendesk tickets and keeps only those with no linked help-center article.
- 3An OpenAI step embeds and clusters the unmatched tickets into candidate topics, discarding clusters below a minimum ticket count.
- 4For each surviving cluster it drafts a Confluence-ready article (title, problem, resolution steps) grounded in the ticket conversations.
- 5It creates the draft page in a staging Confluence space marked as unpublished.
- 6It posts each draft link to the SME review channel in Slack with approve / edit actions.
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 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.