CUSTOMER SUPPORT
Macro Coverage Gap Detector on Ticket Solve
When a ticket is solved without any macro applied, checks whether its answer matches an existing macro and, if not, logs it to Postgres as an uncovered answer so recurring gaps…
How it runs
The automated pipeline, trigger to output.
- TriggerTicket solved in ZendeskZendesk
- LogicKeep only tickets solved without a macro
- ActionEmbed reply and match against macro libraryOpenAI
- LogicBranch on whether a close macro exists
- ActionUpsert uncovered answer into gaps tablePostgres
- OutputPost gap leaderboard to SlackSlack
What it does
Catches the moments your macro library missed. The instant an agent solves a ticket by typing a reply from scratch, it compares that reply against your existing macros; if nothing close exists, it records the gap. Over time the Postgres table shows which hand-written answers recur often enough to deserve their own macro.
When to use it
When you already have a macro library but suspect it has blind spots, and you want a continuously-updated, data-backed list of what to add next rather than a once-a-quarter manual audit.
How it works
- 1A Zendesk ticket-solved event triggers the run.
- 2Filter to only tickets solved without a macro applied.
- 3Use OpenAI to embed the agent's reply and compare it to your existing macro library for a close match.
- 4Branch: if a strong match exists, stop — coverage is fine.
- 5If no match, upsert the reply's intent into a Postgres gaps table, incrementing a count for that recurring answer.
- 6Output the running gap leaderboard to a Slack channel so leads see the top uncovered answers worth turning into macros.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 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.