Skip to content
NEWError doctor and Watchtower: failed n8n runs explained in plain words, and emailed to you. See what is new

Library / Customer Support & Helpdesk

Customer Support & Helpdesk

Answer Employee Questions in Slack with GPT-4o

When a Slack message arrives by webhook, an OpenAI agent answers from a Google Docs handbook with per-channel memory and emails the right department if needed.

What it does

## Remembers the last 5 messages that a user sent Because we are passing the full BODY of the webhook including the channel ID of the user to the memory module, n8n is storing the last 5 slack messages sent to it per slack channel. This means that it will remember all your users conversations separately from one another and not get confused by different requests from different users. You can increase the memory storage by using a different storage medium and increase the number of prompts and responses it should remember.

The steps

  1. Send Initial Message
  2. Send Message
  3. OpenAI Chat Model3
  4. Webhook3
  5. departmentsEmails2
  6. AI Agent2
  7. Slack4
  8. Handbook
  9. No Operation, do nothing
  10. Simple Memory2
  11. Send Email
  12. Delete Initial Message
  13. Bot?
  14. HeadersList

Similar automations