CUSTOMER SUPPORT
Pre-Send Guard That Warns Agents on Stale Macros
When an agent applies a Zendesk macro, an inline webhook check verifies the canned reply against the live help-center article and warns the agent before send if it contradicts…
How it runs
The automated pipeline, trigger to output.
- TriggerZendesk webhook fires when a macro is appliedZendesk
- ActionFetch linked Confluence article bodyConfluence
- ActionLLM scores macro vs. live article contradictionOpenAI
- LogicEnd if aligned; continue only on contradiction
- OutputSend immediate warning DM to the agent in SlackSlack
What it does
This is a just-in-time guardrail. The instant an agent applies a macro to a ticket, a webhook fires a fast check that pulls the macro's linked Confluence article and asks the LLM whether the canned text still holds. If it contradicts the current doc, the agent gets an immediate private warning with the discrepancy so they can edit before the customer ever sees it.
When to use it
Use it when the cost of sending an outdated answer is high (compliance, billing, legal) and you want correction at the point of use rather than after the fact. Best for high-volume queues where periodic audits are too slow to prevent bad replies going out.
How it works
- 1A Zendesk webhook fires when a macro is applied to a ticket.
- 2Fetch the linked help-center article's current body from Confluence.
- 3The LLM judges whether the applied macro contradicts the live article and returns a confidence score.
- 4If alignment is fine, the run ends with no interruption.
- 5On contradiction above threshold, send the agent an immediate Slack DM naming the conflict and the corrected phrasing to use instead.
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
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.