CUSTOMER SUPPORT
Macro Coverage Scorecard to Snowflake
Nightly, computes what share of agent replies were covered by a saved macro versus typed from scratch, broken down by topic and team.
How it runs
The automated pipeline, trigger to output.
- TriggerNightly schedule fires
- ActionPull yesterday's replies + macro-usage eventsZendesk
- ActionTag each reply with a topic categoryOpenAI
- LogicLabel macro-covered vs free-text; aggregate by topic and team
- ActionUpsert daily coverage scorecard rowsSnowflake
- OutputPost coverage summary to leadership SlackSlack
What it does
It turns macro coverage into a measurable metric. Every night it classifies the previous day's agent replies as macro-backed or hand-typed, tags each by topic, and rolls them up into a coverage percentage per topic and per team. The results land in a Snowflake table so leadership can watch coverage trends and spot topics where agents are stuck improvising.
When to use it
Use it when you need a defensible KPI for macro program health, or want to prove that newly authored macros actually moved coverage up over time.
How it works
- 1A nightly schedule starts the run.
- 2Pull yesterday's agent replies and macro-usage audit events from Zendesk.
- 3An OpenAI step tags each reply with a topic category.
- 4A logic step labels every reply as macro-covered or free-text and aggregates coverage by topic and team.
- 5Upsert the daily scorecard rows into a Snowflake coverage table.
- 6Post a short summary of the day's coverage and the biggest gaps to the support leadership Slack channel.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect SnowflakeWarehouses, queries, shares.
- 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.