CUSTOMER SUPPORT
Front Policy-Divergence Flagger: Catch When a Human Edit Broke Policy
When an agent sends a reply in Front, this compares the sent text against the suggested macro draft and your written policy.
How it runs
The automated pipeline, trigger to output.
- TriggerOutbound reply sent in FrontFront
- ActionRead sent reply and original suggested draftFront
- ActionFetch policy document from NotionNotion
- ActionDiff sent text against draft and policyOpenAI
- LogicIf no policy violation, end silently
- OutputPost divergence alert to Slack review channelSlack
What it does
It watches outbound replies in Front and checks whether the agent's edits to a suggested draft stayed within policy. When a sent message promises something the policy forbids (an out-of-window refund, a discount above the cap, a banned commitment), it flags the exact sentence and the rule it violated to a Slack review channel.
When to use it
Use it once agents edit auto-suggested drafts freely and you need a safety net that catches policy drift without reading every ticket. Ideal for refund, billing, and compliance-sensitive inboxes.
How it works
- 1An outbound message sent in Front triggers the run.
- 2The sent reply and the originally suggested draft are read from Front.
- 3The current policy document is pulled from Notion.
- 4OpenAI diffs the sent text against the draft and the policy, returning any violated rules with quoted evidence.
- 5If no violation is found, the run ends silently.
- 6On a violation, a Slack alert names the conversation, the agent, the quoted line, and the broken rule for supervisor review.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect NotionPages, databases, comments.
- 3Connect OpenAIModels, embeddings, files.
- 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.