Classify emails, leads and tickets in Zapier with a model trained on your own decisions

• StayCharted: an Essentials or Business workspace, which includes the API, with at least one published model that reads text. Training works on every plan, Free included, so you can check the model's report first.
• An API key: in StayCharted, Settings → API keys → Create key. A key belongs to one workspace and can use that workspace's published models.
• Zapier: any Zapier account. A two-step Zap (one trigger, Classify Record) runs on Zapier's Free plan. Adding a third step, such as a Filter, Paths or the app that acts on the answer, makes it a multi-step Zap, which needs a paid Zapier plan.

Check current Zapier plans.

StayCharted AI Model Trainer is in early access on Zapier while Zapier reviews it. Until it's listed publicly:

1. Open the StayCharted invitation on Zapier and sign in to Zapier.
2. Accept the invitation. StayCharted AI Model Trainer now appears when you search for apps in the Zap editor, marked "Invite Only".

Once it's public, you can skip this part: search for StayCharted in Zapier.

1. In Zapier, choose + Create → Zaps.
2. Add any trigger for now (Part 3 covers which). Then add an action, search for StayCharted AI Model Trainer and choose Classify Record.
3. Under Account, click Sign in and paste your API key. Zapier checks it by reading your list of models.

Zapier stores the key encrypted and sends it to StayCharted with each request. To stop access, delete the key in StayCharted: every Zap using it stops at once.

1. Trigger: the app and event where your records start, for example:

   • Gmail or Microsoft Outlook: New Email (for sales leads or support requests).
   • Google Sheets: New Spreadsheet Row.
   • Typeform, Jotform or Google Forms: New Entry.
   • HubSpot, Pipedrive or Salesforce: New Contact or New Lead.
   • Your help desk: New Ticket.

   Test the trigger so Zapier has a sample record to map.

2. Action: StayCharted → Classify Record.

   • Model: the dropdown lists the published models this key can use. Choose one.
   • The model's fields appear underneath, named after the columns it was trained on (for example Subject and Message, or File name and Folder). Map each one from the trigger: Gmail's Subject into Subject, the email body into Message, and so on.
   • Fill as many fields as you have. At least one is needed; fields you leave empty are simply not sent.

3. Test the step. You'll see the model's answer for the sample record.

4. Publish the Zap.

Map the same kind of text the model was trained on. A model trained on short subjects and the first paragraph of each email answers best when it gets the same. If you trained on a cleaned-up export, pick the trigger fields closest to those columns.

Classify Record gives later steps these values:

Send unsure answers to a person. Add a Filter (only continue if Needs Review is false) before the step that acts. Or use Paths: one path for answers to act on, one that sends the record to a person, for example a Slack message or an email with the model's answer and a link to the record. Records under the cutoff also wait in StayCharted's Review Queue. Pick one place to review; checking both is wasted work.

Act on the answer. Map Answer (or a Fields value) into the next app: a Gmail label, a CRM owner or stage, a help-desk group, a spreadsheet column. With Paths, give each answer its own route.

• Sales leads from Gmail: classify each inbound email as a lead type (Enterprise, Small business, Partner, Not a lead). Create the contact in your CRM with that type and owner; send Not a lead to a label instead.
• Support requests: classify by category and team, then create the ticket in your help desk with both filled in. Unsure ones go to a triage channel.
• Form entries and spreadsheet rows: add the answer to a column in the same row, so your team sorts by it.

Each starts with a model trained on decisions your team already made: past emails with the lead type you gave them, resolved tickets with their final category and team.

See AI email routing for a shared inbox for training examples and a review workflow.

Paid-search review: Classify rows from an exported search terms sheet and send suggestions to your team for approval. Sort Google Ads search terms with your trained model →. Applying account changes is a separate step.

• Models that read pictures aren't listed in the action yet. Use files or the API for those.
• One record per run. Each Zap run classifies one record. For thousands of existing rows, fill a file or Google Sheet in StayCharted instead.
• It doesn't learn from the Zap. Corrections your team makes in the other apps reach the model when you retrain on a fresh export of those decisions, the same way you trained it.