Automations

Configure AI processing

Define the values you need from a document, such as an invoice number, date, or amount. PigeonFiles adds the extraction results to the submission for review and supported automations. What AI processing does When you enable AI processing on a file upload field, PigeonFiles reads the uploaded files and extracts the columns you define. The extraction runs after upload, then the extracted values become available in submission records and connected automation data where configured. Extracted values can feed into: - Google Sheets rows (as additional columns). - Zapier and Make submission payloads. - Webhook payloads. - Submission records visible in PigeonFiles. Review important extracted values against the original file before using them for financial, legal, or identity decisions. Steps 1. Open the upload page editor. Go to your upload page and open the editor. 2. Open Automation settings. Navigate to Settings > Automation in the upload page editor. 3. Select AI processing. Find the AI processing section. It shows which file upload fields are available for AI extraction. 4. Configure a file field. Click on a file upload field to open its AI processing configuration. AI extraction dialog with an Invoice number column and extraction settings. 5. Add extraction columns. For each piece of information you want to extract from uploaded files, add a column: - Label: the column name, like "Document type," "Invoice amount," or "Tax year." - Column type: choose Text, Number, Date, Yes / no, Currency, Email, or URL depending on the expected value. - Extraction hint (optional): guidance for the AI about where to find the value or how to interpret it. For example: "Use the document text, tables, and visible labels. Return null when unsure." 6. Add instructions (optional). Use the instructions field to give the AI general guidance about the documents it will process on this upload page. This helps when the documents have a consistent format or when you need specific extraction behavior. 7. Apply and save the configuration. Click Done, then Save changes. An enabled page uses the saved settings; enable a disabled page when ready. The AI processing status on the automation hub updates to show the configured file fields and columns, such as "1 file field, 3 columns." 8. Test with a real upload. Submit a document through the upload page. After the submission is processed, open the submission record in PigeonFiles and check that the extracted values appear correctly. Example: extracting invoice details For a bookkeeping upload page that collects invoices from clients: Column label Type Description Vendor name Text The company or person who issued the invoice Invoice number Text The invoice reference number Invoice amount Number The total amount due Invoice date Date The date the invoice was issued When a client uploads an invoice PDF, AI processing extracts these four values. They appear in the submission record and can flow into Google Sheets columns or Zapier/Make payloads. How extracted values reach your workflow After processing completes, check the extracted values in each configured output: - Submission records in PigeonFiles show the extracted columns alongside the uploader's field answers. - Google Sheets rows include extraction values as additional columns if your Sheet connection is active. - Zapier and Make triggers include extraction values as mappable fields. - Webhook payloads include extraction values in the submission data. Troubleshooting Extraction values are empty. The AI may not have found the expected information in the uploaded file. Check that the file is a supported format and that the column descriptions are specific enough to guide extraction. Extraction values are inaccurate. Refine the column descriptions with more specific guidance. For example, instead of "amount," try "the total amount due on the invoice, found near the bottom of the first page." No columns showing. Confirm that you added at least one extraction column to the file field's AI processing configuration and saved the changes. AI processing not running. Check that the published file field has at least one configured column and the workspace has available credits. See AI document processing and credits for supported formats, limits, and skipped processing. Next steps - Automations and integrations. - Send submissions to Google Sheets, log submissions and AI extraction values as spreadsheet rows. Frequently asked questions Does AI processing change my uploaded files? No. AI processing reads the uploaded files and extracts the columns you configure. The original files are delivered to your connected storage unchanged. Can I use AI extraction values in Google Sheets or Zapier? Yes. Extracted values can appear as columns in your Google Sheets log and as fields in Zapier and Make submission payloads. What file types does AI processing support? AI processing is designed for common document and image formats. PDF, JPEG, PNG, and WebP are supported, up to 50 MB per file, subject to processing input limits. See AI document processing and credits.

Configure team email notifications

Open an upload page’s Automation > Email notifications settings to choose the team members who should hear about new submissions. Configurable recipients require Solo or above; recipient limits depend on the plan. Email notifications with the recipient selector and uploader-confirmation control. Choose team recipients 1. Open the page editor and select Automation > Email notifications. 2. Under Submission notifications, click Add recipients. 3. Select the people who need the notification. Review the count and limit in the panel. 4. Click Save changes. On an enabled page this updates the live settings. Enable a disabled page when ready. 5. Complete a small sample submission and check delivery with the selected recipients, including spam or junk folders. Remove recipients who no longer need the information. Selecting a recipient does not grant access to the workspace or the destination folder. Free may send default operational messages to the page creator; it does not include the paid recipient configuration. Current limits The editor shows Send uploaders a confirmation and may show custom subject or message settings. The current submission email delivery process does not use those settings. Do not depend on that switch to email your uploader or on a custom template to change the delivered message. Use the page’s Success content to tell uploaders what happens next. If an acknowledgment email is essential, configure and test a separate Zapier, Make, or webhook workflow with your email service. Collect the address you need and check your service’s sending rules. The standard team message and any verified sender domain are separate from custom message content. If a team email is missing Check the selected recipients, saved configuration, and submission status. Confirm the address and spam folder. If other outputs succeeded, include the submission ID and recipient address when contacting support; do not send the documents or credentials. For Slack, Teams, or another channel, follow the team-channel recipe. The email recipient selector does not connect a channel.

Send submissions to Google Sheets

Connect a Google Sheet to keep a log of incoming submissions, answers, and file references. What Google Sheets logging does When you connect a Google Sheet to an upload page, each new submission creates a row in the spreadsheet. Rows can include: - Uploader name and email (if collected on the page). - Field answers. - Submission timestamp and system columns. - File links (if enabled). This gives your team a running intake log they can filter, sort, and share without opening PigeonFiles. Sheets is for tracking and reporting. The actual files go to your connected storage destination, Google Drive, Dropbox, or OneDrive. Steps 1. Open Automation. In the upload page editor, open Settings > Automation. 2. Select Google Sheets. Choose Google Sheets from the automation list. 3. Start Sheet setup. Click Set up Sheet. If no Google account is connected, click Connect Google and authorize the Google account that should own the spreadsheet. This can be the same account used for storage or a different one. Google Sheets automation settings in the upload page editor. 4. Name the spreadsheet. Fill in Spreadsheet name with a clear name tied to the upload page, like "Client Onboarding Submissions" or "Tax Document Intake Log." 5. Choose the row mode. Choose One row per submission or One row per uploaded file. - One row per submission. File field details are summarized in cells. Best for tracking submissions at a glance. - One row per uploaded file. Submission answers repeat on each file row. Best when you need a file-level checklist. 6. Choose a folder for the spreadsheet. Use Select folder to select where PigeonFiles should create the spreadsheet in Google Drive. 7. Backfill existing submissions (optional). If the upload page already has submissions before you connect the Sheet, keep Include existing submissions selected to import completed submissions. Submissions still transferring files or running AI extraction are added when that work finishes. Leaving this off does not prevent new submissions from syncing. 8. Create the Sheet. Click Create Sheet. PigeonFiles creates the spreadsheet with the header row based on your upload page fields. 9. Submit a test upload. Open the upload page, fill in the fields, attach a file, and submit. 10. Open the Sheet and verify. Use Open Sheet or open the spreadsheet in Google Drive. Check that a new row appeared with the correct field answers, timestamp, and file link. What rows look like Submission mode Client Name Document Type Email Submitted Files File Links Acme Corp Bank Statement anastasia@acme.com 2026-06-21 2 link1, link2 Beta LLC Invoice kyle@beta.com 2026-06-21 1 link1 File mode Client Name Document Type Email Submitted File Name File Link Acme Corp Bank Statement anastasia@acme.com 2026-06-21 acme-q2-statement.pdf link Acme Corp Bank Statement anastasia@acme.com 2026-06-21 acme-q2-backup.pdf link Beta LLC Invoice kyle@beta.com 2026-06-21 beta-invoice-0621.pdf link Columns follow your upload page New questions and AI extraction outputs get columns automatically when their first submission arrives. You can move or hide whole columns; PigeonFiles continues writing to the matching fields. Duplicate headings do not mix up answers. Renaming a question updates its generated heading. If you have already given the column a custom heading in Google Sheets, your heading stays. Removing a question keeps its old column and historical values. Pending submissions from the earlier page version can still fill that column. Adding a new question with the same name creates a separate column. If you delete a column that an upcoming submission needs, PigeonFiles creates it again at the right. Previously delivered rows are not replayed into the replacement column. Change row mode Open Automation > Google Sheets, choose Change row mode, then Create tab. PigeonFiles creates a new tab in the same spreadsheet and sends future submissions there. The previous tab and its history stay in place. Include existing submissions is off for this change. Select it if you also want to import completed submissions into the new tab. Setup lists Google accounts you connected. A spreadsheet connected by a teammate remains visible, but changes requiring their Google authorization must be made by that account's owner. Troubleshooting Rows aren't appearing. Check Automation > Google Sheets on the upload page. If delivery shows an error, the Google account may need reauthorization. Missing columns. New field columns appear when a submission containing those fields is delivered. Check that the page changes are published and that the submission has finished processing. Google authorization expired. Use Reconnect Google from Automation > Google Sheets when it appears. Sheets delivery will resume after reauthorization. Spreadsheet vs. storage. The Sheet logs submission data and file links. The files themselves are in your connected storage destination, not in the spreadsheet. Next steps - Automations and integrations. - Track client documents in Sheets. Frequently asked questions Does Google Sheets store the uploaded files? No. Google Sheets logs the submission data, field answers, timestamps, file links, and delivery status. The actual files go to your connected storage destination (Google Drive, Dropbox, or OneDrive). Can I choose between one row per submission or one row per file? Yes. Submission mode creates one row per submission with file details summarized. File mode creates one row per uploaded file with submission answers repeated on each row.