CUSTOMER SUPPORT
Map Orphan Macros to Help-Center Articles and Flag Coverage Gaps
Finds Zendesk macros that aren't linked to any help-center article, uses the LLM to match each to the most relevant Confluence doc.
How it runs
The automated pipeline, trigger to output.
- TriggerManual run kicks off the mapping pass
- ActionList macros and detect those missing a help-center linkZendesk
- ActionSearch Confluence for candidate articles per macroConfluence
- ActionLLM picks best match and scores confidenceOpenAI
- LogicBranch into mapped, low-confidence, and no-match groups
- OutputWrite coverage map to Confluence and post counts to SlackConfluence
What it does
Drift detection only works when every macro has a source-of-truth article to compare against. This workflow tackles the blind spot: it finds macros with no Confluence link, semantically matches each one to the best candidate article, and where no good match exists, flags it as either an orphan macro to retire or a missing doc to write. The result is a coverage map plus a gap list.
When to use it
Run it as a one-time cleanup or quarterly hygiene pass before relying on the other drift audits. Ideal when your macro library has grown organically and you no longer know which canned answers are backed by documentation.
How it works
- 1A manual run kicks off the mapping pass.
- 2List all Zendesk macros and detect which ones lack a help-center link.
- 3Search the Confluence knowledge base for candidate articles per unlinked macro.
- 4The LLM picks the best-matching article and scores confidence, or returns no match.
- 5Branch results into mapped, low-confidence, and no-match groups.
- 6Write the full coverage map and gap list to a Confluence audit page and post the headline counts to Slack.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect OpenAIModels, embeddings, files.
- 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.