CUSTOMER SUPPORT
KB Search-Miss Miner: Route Doc Gaps to Engineering When No Article Exists
Daily, it joins help-center search queries that returned zero results with tickets that had no KB match, drafts an article when docs can fix it.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule fires
- ActionJoin zero-result searches with unanswered tickets in ZendeskZendesk
- LogicClassify each gap as documentable or product issueOpenAI
- ActionDraft article as Notion review page for doc gapsNotion
- ActionFile Linear issue for product gaps with evidenceLinear
- OutputPost triage digest to SlackSlack
What it does
Not every KB gap is solved by writing an article. This workflow distinguishes documentation gaps from product gaps: it cross-references failed help-center searches with unanswered tickets, drafts an article when the answer exists, and escalates to engineering when the real fix is a product change.
When to use it
Use it when failed searches and confused tickets point at the same topics, and you need to separate "we should document this" from "the product needs to change." Strong fit for teams who triage in Linear.
How it works
- 1A daily schedule triggers the run.
- 2It pulls zero-result help-center search queries from Zendesk and joins them with tickets that closed without a KB match.
- 3An OpenAI step classifies each clustered gap as documentable or a product/engineering issue.
- 4Documentable gaps get a drafted article created as a Notion review page.
- 5Product gaps get a Linear issue filed with the supporting ticket and search evidence.
- 6It posts a triage digest to Slack summarizing both branches.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect NotionPages, databases, comments.
- 4Connect LinearIssues, projects, cycles, triage.
- 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 this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.