Automating document intake from email

Connect Gmail, build an automation whose trigger matches the messages you want, and Document Blueprint pulls each match in — categorizing, extracting, and filing it to a case without manual upload.

Once an automation is on, every matching message becomes a case in the destination mailbox. Your team stops thinking about ingestion and starts thinking about the work.

What the automation owns

A Gmail automation binds one trigger to one destination tuple:

1. Trigger — Gmail filters: subject contains, sender contains, label, read status. AND-logic; first match wins.
2. Destination — the mailbox the case lands in, the file category tag, and how duplicates are handled.
3. Extract (optional) — a template that runs extraction inline. Picking a template auto-resolves the source and category.

There are no schedule or cron triggers. Delivery is push-based — Gmail pipes new-message events into Document Blueprint via Pub/Sub; Drive uses a Changes API webhook channel — so matching messages typically appear within a minute of arrival.

Walkthrough: vendor invoices from Gmail

Your AP team forwards every vendor invoice to a Gmail label Paperwork/Invoices. You want each one to become a case in the AP mailbox, extracted with your AP cover sheet template.

1. In Settings → Integrations, click Connect Gmail and grant access.
2. Open the workspace sidebar's Automations drawer and click + New Automation.
3. On the Trigger node, pick Gmail and set Gmail label to Paperwork/Invoices. Leave Capture From Email at its default of Sender + Subject + Files.
4. On the Destination node, pick the AP mailbox and set Duplicate handling to Re-extract (so re-sends update the existing case).
5. On the Extract Data node, check Extract data with a template, pick the AP cover sheet template, and Done. The category is derived from the template's source.
6. Click Save.
7. Forward a test invoice to the label. Within a minute, it appears in the AP mailbox.

TriggerGmail, label Paperwork/Invoices

DestinationAP mailbox, Re-extract

ExtractAP Cover Sheet template

Patterns that hold up

One label per process

Use a separate Gmail label for each automation. Sharing a label across automations makes debugging hard.

Capture only what you need

The capture pills (Sender, Subject, Body, Files) control what the automation pulls into the pipeline. Keep Body off unless your template uses email_body_context fields — bodies add noise.

Test with one item before scaling

The first version of any automation has some misconfiguration. Send one test message before you point a high-volume label at it.

Troubleshooting

Automation stopped firing. Open the card. An amber Auto-paused chip means it was disabled by the system; the banner explains why — usually OAuth expired — reconnect Gmail or Connected user removed from workspace.

Messages match but no case appears. Open the automation's Activity log under the canvas and find the entry for that message. It tells you exactly which step failed.

Wrong mailbox or category. Open the automation; the Destination node holds the mailbox; the category is whatever the Extract template's linked source declares. If you need a different category, switch the template (or turn extraction off and pick a category directly).

Some attachments are skipped. If Files is off in the capture pills, attachments are ignored. Also: if the destination's category or the extraction template can't be resolved at run time, ingestion is skipped on purpose — fix the missing piece and the next message goes through.

Related

• What automations are
• Creating an automation
• Triggers