AI triage
You can now create rules that check the intent of a conversation.
You describe the email in a short phrase. When a new email arrives, Fernand compares it with every live rule that uses this trigger and runs the one that fits best. If nothing is a clear match, the email lands in your inbox as before.
A few worth setting up first:
- Cold outreach. When a conversation is about "Cold outreach, spam or phishing" and the contact is not a customer, mark it as spam. Start with a tag or a note until the matches look right, so a real customer's clumsy first email stays visible.
- Billing. When it's about "Billing question, invoice, or refund" and the contact is on a paid plan, tag it and assign it to the person who handles money.
- Bug reports. Tag it, assign it, and open the issue in Linear or GitHub from the same rule. A webhook can post to any URL you control.
- Cancellations. Tag it, assign it to a founder, and notify them. Leave the reply and the close to a person.
- Outages. Use the same description on two rules. During business hours, tag it and notify the team. Outside business hours, page the on-call engineer.
Anything a normal rule can do still works on an intent: write an AI draft, insert a reply and close, snooze, forward, or leave a note for the next person.
Add it from Settings → Rules → Add rule. Under When, choose A conversation and is about….