CUSTOMER SUPPORT
Front Macro-Gap Detector: Monthly Coverage Gap Report
Monthly, measures what share of Front replies were hand-typed versus macro-sent, identifies the biggest uncovered topics with an LLM.
How it runs
The automated pipeline, trigger to output.
- TriggerMonthly schedule starts the run
- ActionPull the month's outbound Front repliesFront
- LogicSplit macro-sent vs manual; compute coverage ratio
- ActionWrite narrative gap report with top uncovered topicsOpenAI
- ActionSave full report to a Coda docCoda
- OutputPost headline summary and link to SlackSlack
What it does
Gives support leadership a monthly read on how well the macro library actually covers real conversations. It computes the manual-versus-macro reply ratio, names the topics driving the most uncovered manual work, and quantifies the time those gaps cost so you can prioritize what to build next.
When to use it
Use it for monthly QBRs or team reviews where you need evidence, not anecdotes, about where saved replies are falling short. Best for managers who report on deflection and agent efficiency.
How it works
- 1A monthly schedule starts the run.
- 2It pulls the month's outbound Front replies and splits them into macro-sent versus hand-typed.
- 3A logic step computes the coverage ratio and groups manual replies by theme.
- 4An OpenAI step writes the narrative report: top uncovered topics, estimated agent time spent, and recommended macros to create.
- 5The full report is saved to a Coda doc and a short headline summary is posted to Slack with a link.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect CodaDocs, packs, automations.
- 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.