CUSTOMER SUPPORT
Trace Low-CSAT Zendesk Tickets to Doc Gaps and Open Asana Fixes
On each low CSAT rating in Zendesk, an LLM diagnoses whether a missing or wrong help article caused the bad experience and, when it did, opens an Asana task to fix the specific…
How it runs
The automated pipeline, trigger to output.
- TriggerLow CSAT rating recorded in ZendeskZendesk
- ActionPull ticket conversation and referenced articlesZendesk
- LogicClassify doc-related root cause with LLMOpenAI
- ActionLocate the relevant Confluence pageConfluence
- ActionOpen Asana fix task linked to ticket and pageAsana
- OutputNotify docs owner in SlackSlack
What it does
Uses unhappy customers as a precision signal for doc problems. When a ticket gets a low satisfaction score, it determines whether weak documentation was the root cause and routes a targeted fix to the doc owner.
When to use it
Use it when you collect CSAT in Zendesk and want to close the loop between dissatisfaction and documentation — catching not just missing docs but outdated or confusing ones that frustrate customers.
How it works
- 1A new low CSAT rating (negative satisfaction) in Zendesk triggers the run.
- 2Pull the full ticket conversation and any articles the agent referenced.
- 3An LLM classifies the root cause: doc missing, doc outdated, doc unclear, or unrelated to docs.
- 4Branch: if the cause is unrelated to documentation, stop.
- 5For doc-related causes, locate the relevant Confluence page (or note that none exists).
- 6Open an Asana task describing the exact fix needed, linked to the ticket and the page.
- 7Notify the docs owner in Slack with the diagnosis and priority.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ConfluenceSpaces, pages, blueprints.
- 4Connect AsanaTasks, projects, milestones — everywhere.
- 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 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.