CUSTOMER SUPPORT
Cluster Repeated Zendesk Tickets into ReadMe Article Drafts
On a weekly schedule, groups recently solved Zendesk tickets by topic, finds the clusters with no matching help-center article.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionFetch solved tickets from ZendeskZendesk
- ActionCluster tickets by topic with OpenAIOpenAI
- LogicKeep clusters above volume threshold
- ActionCheck ReadMe for existing coverageReadMe
- ActionDraft article for each uncovered gapOpenAI
- OutputCreate unpublished ReadMe draftsReadMe
What it does
Finds the questions your team answers over and over and turns the biggest gaps into ready-to-edit help-center drafts. Every week it pulls solved Zendesk tickets, clusters them by underlying question, checks which clusters have no existing ReadMe article, and writes a first-draft doc for each uncovered topic.
When to use it
Run this when your support volume is dominated by a handful of repeat questions and your knowledge base hasn't kept up. It's the backlog-to-content pipeline for teams that want self-serve deflection without manually triaging hundreds of tickets.
How it works
- 1A weekly schedule fires the run.
- 2Pull the last 7 days of solved tickets from Zendesk.
- 3An OpenAI step clusters tickets by underlying question and labels each cluster with a candidate title.
- 4A logic step keeps only clusters above a volume threshold (e.g. 5+ tickets).
- 5For each surviving cluster, search ReadMe for an existing article on that topic; drop clusters already covered.
- 6OpenAI drafts a structured article (problem, steps, related links) per remaining gap.
- 7Create each draft as an unpublished ReadMe page for an editor to review.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ReadMeAPI docs, changelog, auth.
- 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.