CUSTOMER SUPPORT
Quarterly VoC theme warehousing from Zendesk into BigQuery
Each quarter, classify all Zendesk tickets into product-feedback themes and load the labeled.
How it runs
The automated pipeline, trigger to output.
- TriggerQuarterly schedule fires
- ActionExport quarter's Zendesk tickets with metadataZendesk
- ActionLabel tickets with theme and sentiment (OpenAI)OpenAI
- LogicValidate labels against canonical taxonomy
- ActionLoad labeled rows into BigQuery tableBigQuery
- OutputPost load summary to data channelSlack
What it does
Builds a durable analytics layer for support feedback. It classifies a full quarter of Zendesk tickets into product-feedback themes, attaches structured metadata (theme, sentiment, segment, product area), and loads the labeled rows into a BigQuery table so the data team can run trend, retention, and segment analysis in SQL or a BI tool.
When to use it
Use it when ad-hoc theme reports aren't enough and you want voice-of-customer as a first-class dataset, queryable alongside product usage and revenue. Ideal for analytics teams owning the customer-insight warehouse.
How it works
- 1A quarterly schedule fires the run.
- 2Export all Zendesk tickets from the quarter with metadata and conversation text.
- 3An OpenAI step labels each ticket with theme, sentiment, and product area in a structured schema.
- 4A logic step validates and normalizes the labels against the canonical theme taxonomy.
- 5Load the labeled rows into a partitioned BigQuery table for analysis.
- 6Output a load summary (rows written, new themes detected) to the data channel.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect BigQueryDatasets, queries, schemas.
- 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.