CUSTOMER SUPPORT
Decaying Article Agent Rewrite for Confluence
When an article is flagged as decaying, an agent reads the recent tickets it failed to deflect, drafts an updated version with OpenAI.
How it runs
The automated pipeline, trigger to output.
- TriggerWebhook: article flagged decayingHTTP webhook
- ActionFetch recent undeflected tickets from ZendeskZendesk
- ActionRead current page from ConfluenceConfluence
- ActionDraft revised article with OpenAIOpenAI
- ActionSave review draft to ConfluenceConfluence
- OutputSend Slack review request to ownerSlack
What it does
Closes the loop from detection to draft. When a knowledge article is flagged as decaying, this agent investigates why — pulling the recent tickets that the article should have deflected but didn't — and produces a concrete rewrite that addresses the new questions readers are actually asking, staged for human review.
When to use it
Use it when detection alone isn't enough and you want the first draft of a fix automatically prepared. Ideal for teams whose canonical articles live in Confluence and who want a reviewer, not an author, in the loop.
How it works
- 1A webhook fires when an upstream monitor flags an article as decaying.
- 2The agent fetches the article's recent unresolved Zendesk tickets to find the gaps the page no longer covers.
- 3It reads the current Confluence page content for context.
- 4Using OpenAI, it drafts a revised version that folds in the new failure modes and updated steps.
- 5It writes the draft as a new Confluence version marked for review, never overwriting the live page.
- 6It posts a Slack review request to the page owner with a before/after summary.
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.
- 5Connect HTTP webhookTrigger any URL on agent actions.
- 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 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.