CUSTOMER SUPPORT
Draft Knowledge Base Articles from Recurring Ticket Clusters
On a schedule, identifies ticket clusters that lack a matching help-center article and drafts a KB candidate in Notion for each gap, ready for an editor to review and publish.
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule triggers run
- ActionPull resolved tickets and cluster by themeZendesk
- ActionList existing Help Center articlesZendesk
- LogicKeep clusters with no KB coverage
- ActionDraft KB article per gapOpenAI
- OutputCreate draft pages in Notion review DBNotion
What it does
Finds the recurring questions your customers keep asking that your knowledge base doesn't yet answer, and writes a first-draft article for each one. It cross-checks ticket themes against existing Zendesk Help Center articles so you only draft what's genuinely missing.
When to use it
Use it when your KB is lagging behind real support demand and you want a steady pipeline of well-targeted article drafts instead of guessing which topics to document next.
How it works
- 1A schedule triggers the run.
- 2It pulls recently resolved Zendesk tickets and groups them into recurring root-cause clusters with OpenAI.
- 3It lists existing Help Center articles from Zendesk and asks the model which clusters have no adequate coverage.
- 4A logic step keeps only the uncovered, high-volume clusters.
- 5For each gap, OpenAI drafts a structured KB article: problem, cause, step-by-step fix, and related links, grounded in the actual ticket resolutions.
- 6Each draft is created as a page in a Notion review database tagged "KB candidate."
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect NotionPages, databases, comments.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, 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.