CUSTOMER SUPPORT
Nightly Macro-Drift Audit Against Help-Center Articles
Each night, compares every Zendesk macro against its linked Confluence help-center article and flags macros whose canned text now contradicts the current published doc.
How it runs
The automated pipeline, trigger to output.
- TriggerNightly schedule fires the audit
- ActionList active macros and their linked help-center pagesZendesk
- ActionFetch current Confluence article bodiesConfluence
- ActionLLM classifies each macro as aligned, stale, or contradictoryOpenAI
- LogicKeep only stale and contradictory macros
- OutputPost ranked drift digest to support-ops SlackSlack
What it does
This workflow runs a nightly audit that catches support macros that have silently fallen out of sync with the help center. It pulls every active Zendesk macro, finds the Confluence article each macro references, and asks an LLM to judge whether the canned reply still matches what the article says today. Any contradiction becomes a triaged drift report.
When to use it
Run this when your help center is updated more often than your macros, and agents keep pasting answers that no longer match the documented policy (refund windows, SLA timing, feature availability). It is built for support ops teams who own both the macro library and the knowledge base.
How it works
- 1A nightly schedule fires the audit.
- 2List all active macros from Zendesk and the help-center page each one links to.
- 3Fetch the current published body of each linked Confluence article.
- 4For each macro, the LLM compares canned text to the live article and classifies it as aligned, stale, or contradictory with a short rationale.
- 5Filter to only stale and contradictory results.
- 6Post a ranked drift digest to the support-ops Slack channel with macro name, conflict, and article link.
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.