CUSTOMER SUPPORT
Front Edit-Divergence Coaching Log: Track How Agents Rewrite Suggestions
When an agent sends a reply built from a suggested macro, this measures how far the sent text diverged from the suggestion, logs the edit and reason to Airtable.
How it runs
The automated pipeline, trigger to output.
- TriggerOutbound reply sent in FrontFront
- ActionRead sent text and suggested draftFront
- ActionScore divergence and classify edit reasonOpenAI
- ActionAppend record to Airtable coaching logAirtable
- LogicIf agent crosses rolling drift threshold, branch to coaching
- OutputSend private coaching DM in SlackSlack
What it does
It quietly tracks how much agents change auto-suggested drafts before sending, building a coaching dataset. For each reply it scores the edit distance, classifies why the agent changed it (tone, accuracy, missing info, or personalization), logs the record, and sends gentle individual feedback when a pattern of unhelpful drift appears.
When to use it
Use it to improve both your macros and your agents. High-divergence macros signal templates worth rewriting; recurring per-agent drift signals a coaching opportunity. This is about quality, not policy enforcement.
How it works
- 1An outbound reply sent in Front triggers the run.
- 2The sent text and the suggested draft are read from Front.
- 3OpenAI computes how far the reply diverged and classifies the edit reason.
- 4The conversation, macro, divergence score, and reason are appended to an Airtable coaching log.
- 5If an agent crosses a rolling drift threshold, a private Slack DM with a coaching note is sent.
- 6Otherwise the run ends after logging.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect AirtableBases, tables, views, 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.