CUSTOMER SUPPORT
Live Deflection-Failure Catcher: Draft KB Article When the Bot Fails
When an Intercom resolution bot fails to deflect a conversation and it escalates to a human, this captures the unanswered question, drafts a Notion KB article on the spot.
How it runs
The automated pipeline, trigger to output.
- TriggerIntercom conversation escalates from bot to humanIntercom
- LogicConfirm bot deflection failed (no article resolved it)
- ActionExtract question and check for duplicate KB titleOpenAI
- ActionDraft a how-to article for the new gapOpenAI
- ActionCreate draft in Notion review databaseNotion
- OutputDM the topic owner in Slack to approveSlack
What it does
It treats every bot deflection failure as a signal that the knowledge base has a hole. The moment a conversation escalates from the AI bot to a human agent, it records what the customer actually asked and turns that into a proposed article so the gap is closed before the same question returns.
When to use it
Ideal for teams running an Intercom Fin/resolution bot who want their self-serve content to learn from every miss in near real time, rather than in a quarterly audit.
How it works
- 1An Intercom conversation event triggers when a bot conversation is reassigned to a human team.
- 2A filter confirms the bot attempted and failed deflection (no article resolved the issue).
- 3An OpenAI step extracts the underlying question and checks it against existing Notion KB titles to avoid duplicates.
- 4If no close match exists, it drafts a concise how-to article.
- 5It creates the draft in a Notion review database tagged by product area.
- 6It direct-messages the mapped topic owner in Slack with the draft and an approve link.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect NotionPages, databases, comments.
- 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.