Mailhook and Knowledge: Intake Form PDF Extraction Template

When a customer registration PDF is emailed to your Mailhook address, Spojit reads it and pulls out the contact and account fields ready for the next step.

What It Builds

A Mailhook trigger gives this workflow its own dedicated email address. When an intake form PDF arrives, an Attachment node fetches the file bytes and a Knowledge node embeds it into a transient, single-run collection. A second Knowledge query in Query mode then reads that collection back and returns the customer name, email, phone, and account number as clean, structured fields you can route onward.

The Prompt

Paste this into Miraxa and it builds the workflow, connecting the tools for you:

Build a workflow that triggers when a customer registration PDF is emailed to a mailhook. Take the PDF attachment, embed it into a transient knowledge collection, then query it to extract the customer's full name, email, phone number, and account number as structured fields, and log the result.

Connectors Used

Mailhook - the trigger: any email to the generated address starts a run.
Attachment - fetches the PDF bytes from the inbound email.
Knowledge - embeds the PDF into a transient collection, then queries it for the fields.

Customize It

Change which fields to extract by editing the list in the prompt (add address, date of birth, or preferred pharmacy). You can also swap the final step to email a confirmation or push the extracted record to another system instead of just logging it.

Tips

A transient collection embeds, queries, then discards in a single run: ideal for one-off intake forms with no storage to manage.
Add a Response Schema to the Knowledge query so every field comes back as reliable JSON.
Knowledge OCR handles scanned PDFs, so photographed or faxed forms still parse.