Document Processing and Extraction

Document processing turns a stored file into usable workspace context. Eigenn classifies supported files, produces searchable text and summaries, adds tags, extracts structured financial fields when possible, and proposes transaction matches for eligible documents.

Eigenn shows the process so that you can check it. The file status, extraction status, confidence, field evidence, corrections, and match decisions stay visible. Eigenn does not hide them behind a single “AI complete” state.

Prerequisites

Before you use the processed data:

• Upload the file to the correct workspace under Vault.
• Keep the source document available for comparison.
• Use a role with write access to edit extracted fields or resolve matches.
• Connect transaction data for transaction suggestions.
• Give the background process time after the file upload finishes.

Find Process Details

1. Select Vault in the primary sidebar.
2. Open a file, or open its action menu and select View details.
3. Check File Information → Status and Progress.
4. Check Summary, Extracted Data, Suggested matches, Tags, and Related Files when those sections appear.
5. For a cross-document queue, select Vault → Workspace.
6. Check Review queue, Suggested matches, Status center, and Audit trail.

Processing Lifecycle

The file-processing state and the financial-extraction state connect to each other, but they answer different questions.

File-processing status

While a job runs, Progress can show a percentage and the current stage. If detailed progress is not available, the interface still shows a Processing indicator that pulses.

Extraction status

Use the Extraction status Vault filter to distinguish:

• Pending
• Extracted
• Verified
• Edited
• Failed
• Skipped
• Needs review

A file can be Ready at the file level while structured extraction shows Skipped or Needs review. Ready means that you can use the file. It does not guarantee that Eigenn extracted every financial field.

What General Processing Adds

For supported files, general processing can add:

• A generated title
• A summary
• Searchable text
• Language and document-type context
• Tags that Eigenn generates automatically
• An index for semantic search

Supported processing formats include:

• PDF
• Common image formats
• CSV, plain text, and Markdown
• Microsoft Word, Excel, and PowerPoint formats
• OpenDocument text, spreadsheet, and presentation formats
• RTF

Eigenn converts HEIC images for image processing. Eigenn routes other image formats through image classification. A format outside the supported processing set can stay in the Vault without generated context.

Structured Financial Extraction

For recognized financial documents, Extracted Data can include:

• Document type
• Counterparty
• Amount and currency
• Tax amount
• Issue date
• Due date
• Statement or service period
• Invoice or receipt line items
• Statement transactions and balances

Not every field appears on every document. Empty or irrelevant fields stay out of the view.

The document-type badge shows the detected category. Before human verification, the panel can show an overall confidence percentage. Individual fields can also include evidence such as confidence, validation state, validation issues, source path, and extraction source.

Review warnings

Eigenn can set Needs review for conditions such as:

• A low text signal
• No readable text sample
• A need for OCR
• An unsupported extraction format
• A MIME type that does not match the file extension
• Validation issues in extracted totals or fields

These warnings do not automatically mean that you cannot use the stored file. They mean that a person needs to compare the source. That person then adds or corrects the details.

Confirm or Correct Fields

1. Open Extracted Data.
2. Select Verify / Edit.
3. Check Counterparty, Amount, Currency, Tax amount, Issue date, and Due date.
4. Correct the values that do not match the source.
5. Select Save.

When you save a correction, Eigenn marks the extraction as edited. Eigenn records the current user as the person who confirmed it. Eigenn records the changed fields. Eigenn then refreshes the search representation of the document.

The panel can show:

• Activity for extraction and correction events
• Versions for recent document versions
• Field-level before-and-after details for recorded corrections

Check Line Items and Statement Rows

When the extraction contains invoice or receipt line items, check:

• Description
• Qty
• Unit price
• Amount

When it contains statement transactions, check:

• Date
• Description
• Amount
• Balance

Compare totals with the source document before you use the data in a decision. A high confidence value gives support. It is not a substitute for a check against the source.

Resolve Transaction Suggestions

Eligible invoices, receipts, and expenses can get suggested transaction matches when an amount and issue date are available.

1. Open Suggested matches.
2. Compare the transaction name, date, amount, currency, and confidence.
3. Select Link for the correct suggestion.
4. Select Dismiss for an incorrect suggestion.

For a queue-based check, open Vault → Workspace → Suggested matches. You can resolve one suggestion at a time. You can also use Link visible and Dismiss visible after you check every item in the visible set.

Work the Review Queue

When extracted data needs attention, Vault → Workspace → Review queue lists the visible documents and their status, document type, and confidence.

• Select Repair failed to retry the visible failed or needs-review extractions that are eligible for repair.
• Select Verify visible to confirm the visible queue entries.
• Use Audit trail to confirm that Eigenn recorded the changes.
• Use Export CSV to download extracted rows in Extracted, Verified, Edited, or Needs review states.

Use bulk verification only after you examine the visible set. It is an operational shortcut, not an automatic validation step.

Confirm Success

The process is complete enough for use when:

• File Information → Status shows Ready
• The preview opens and the file name, size, and type are correct
• The summary and tags describe the source accurately, when they appear
• Extracted Data agrees with the source, or you corrected it and it shows Verified
• A resolved suggestion shows Linked or disappears from the pending match queue
• Activity or Audit trail records the human correction or bulk action

For a non-financial or unsupported file, success can mean that the file is Ready. You can preview it, search it by its stored metadata, and download it. Not every file needs structured fields.

Limits and Edge Cases

• Upload completion and process completion are separate. The success toast confirms storage before Eigenn guarantees every background result.
• Vault accepts up to 25 files per batch and 100 MB per file. Eigenn rejects an empty file.
• Eigenn can store an unsupported processing format without a summary, extracted fields, or generated tags.
• Structured extraction applies to recognized financial documents that have usable text. A non-financial document can show Skipped and no Extracted Data panel.
• Image classification and structured financial extraction are separate capabilities. An image can get a title or summary without structured fields.
• Scanned or low-text files can need a check even when the preview looks correct.
• Suggested matches need enough extracted context and available transaction data.
• Verify visible affects every document that the review section shows now.
• Link visible and Dismiss visible affect every suggestion that the match section shows now.
• When you correct extracted fields, Eigenn does not change the pixels or text in the original file that you uploaded.

Troubleshoot

Status remains Pending or Processing

Refresh the file details. Check if Progress changes. Confirm that the upload completed and that the file is not empty. If the status does not change, copy the Storage Path. Give the file name and the upload time when you contact support.

The status shows Failed

Open Vault → Workspace → Review queue. Use Repair failed when the document appears there. Then examine the individual document again. If repair does not resolve it, convert the source to PDF or another supported format that contains text. Then upload a new copy.

The file is Ready but Extracted Data does not appear

The file can be non-financial, unsupported for structured extraction, image-only, or skipped on purpose. Check Summary, Tags, File Information → Document Type, and the Extraction status filters. Use the original file as the source of truth when no structured panel appears.

Extracted Data says Needs review

Read the review reasons. Compare each displayed field with the source. Select Verify / Edit. Save the corrections. For a scanned PDF with no readable text, a cleaner text-based PDF can produce a better result.

A field has low confidence

Read the evidence detail beneath the field. Check validation issues, the cited source path, line-item totals, and currency. Correct the field. Do not depend on the overall confidence badge.

No transaction suggestions appear

Confirm that the document is an invoice, receipt, or expense with an amount and issue date. Confirm that the workspace has relevant transaction data. You can still reconcile receipt work manually from Workspace Inbox and Approvals.

Related Pages

• Document Vault
• Organize and Share Documents
• Workspace Inbox and Approvals
• Transactions
• Support