Skip to main content

Capture inbox

What this page is — the front door for documents that exist outside Papers: PDFs, text files, images, voice memos and meeting recordings, uploaded by people or pushed in by automated sources, then classified and converted into real documents.

What it is for — so the agreements that arrived as attachments come inside the system, where the register, retention and search apply to them.

The problem it solves — agreements received as attachments never enter the register, so their dates, retention and search coverage are missing.

Route: /org/papers/capture · Permissions: Show the Capture Inbox sidebar entry. for the page; Create documents from a type. to upload, mint sources and convert; Use AI drafting/extraction/Q&A for documents. to classify.

Figure 1 — Items move from received, to classified, to converted.

1. What it is​

Every item follows one path:

StatusMeansNext
received (grey)The file arrived; nothing has read itClassify, Convert or Discard
classified (blue)The AI read it and suggested a type and a summaryConvert
converted (green)It became a Papers document, with the original file attachedOpen document
discarded (red)Rejected — the stored file is deleted; the row stays for audit—

How a file is read before classification:

FileRead byWorks for
PDF, TXTIts embedded text layerBorn-digital documents — invoices, contracts, letters
Scanned PDF, PNG, JPG, TIFFSame — but a scan has no text layerRefused
MP3, WAV, M4A, AAC, OGG, WEBM, MP4, MOVSpeech-to-text transcriptionRecordings with discernible speech
Scans and photos cannot be classified on this deployment

Images and scanned PDFs are accepted uploads, but there is no image OCR. Classify returns: no text layer was found in this document — it looks like a scan or photo. Image OCR is not available on this deployment: upload a text-based PDF, or paste the content as a .txt capture.

You can still Convert without classifying, picking the type yourself; the file is attached, but no text is extracted for AI to structure.


2. Why you would use it​

  • Nothing important stays outside the system. A counter-signed PDF emailed back becomes a document with an obligation register and a retention date.
  • Automated feeds need no polling. A mail pipe or scanner script pushes files to a secret URL.
  • Recordings become documents. A meeting recording is transcribed and classified like any other text.
  • Rejections are auditable. A discarded row remains, showing what arrived and that it was rejected.

3. Step by step​

Upload — drag up to 20 files onto the drop-zone, or click it.

Classify — press Classify (or Transcribe & Classify for recordings). The chip shows the suggested type code and a one-to-two-line summary.

Convert — press Convert. The suggested type is used if classified; you land in the new document's workspace with the file attached. Use Structure captured content there to fill fields.

Automate — Inbound sources → New source → name and kind → Create → copy the URL now — the token is shown once.


4. Field reference​

Limits​

RuleValue
Document formatsPDF, PNG, JPG, JPEG, TIFF, TXT — 20 MB each
Recording formatsMP3, WAV, M4A, AAC, OGG, WEBM, MP4, MOV — 100 MB each
Files per upload20
Pages read100 (papers.ocr_max_pages)
Characters read400,000 (papers.ocr_max_chars)
Scan detectionUnder 40 characters of text is treated as a scan (papers.ocr_min_chars)
Transcription timeout300 seconds (papers.stt_timeout_s)

Classify and Convert​

StepUsesRefusals
Classifypapers_auto_classify — 450 credits est. · 1,800 max per filecapture item in status "converted" cannot be classified · no text could be extracted from this file · the scan message above
ConvertNo AI; no creditsa document type is required — pass type_id or type_code, or classify the item first · suggested type code "x" does not resolve to an active document type in this scope…
Discard—converted capture items cannot be discarded

Re-classifying replaces the previous suggestion.

Inbound sources​

Field / columnHolds
NameRequired — what a colleague will recognise
KindEmail, Webhook / integration, Watch folder, Mobile capture app — a label only
TokenShown once; only its hash is stored
Agent callPOST multipart form data, file field files, same formats and limits as upload
Ingested files, Last ingestHealth: a source that has not ingested for a week has probably broken at the sending end
RevokeKills the token at once; cannot be undone — mint a new source to restore

5. Worked example​

The accounts team receives supplier invoices by email and signed contracts from reception.

  1. They mint a source Accounts mailbox pipe, kind Email, and paste the URL into the mail-server script. Over a week it ingests 142 files.
  2. Most invoices are born-digital PDFs. Classify on one returns chip inv and "Tax invoice from Gatiro Retail for 45,900". Convert — the invoice is a document with the PDF attached. 450 credits.
  3. Reception scans a counter-signed NDA as a JPG. Classify is refused: no text layer. They press Convert directly, choose Mutual NDA (India), and fill the fields by hand from the attached image.
  4. A sales manager drops client-call.m4a. Transcribe & Classify takes two minutes and suggests meeting_minutes. Converted; the transcript feeds Structure captured content.
  5. Three spam PDFs from the mail pipe are discarded; their rows remain, action-less.

6. The admin contract​

Must be trueWhereWhat breaks without it
The role holds Create documents from a type.Role editorNo drop-zone, sources or Convert
The role holds Use AI drafting/extraction/Q&A for documents.Role editorNo Classify
Active types exist for what arrivesType DesignerSuggested codes do not resolve; Convert needs a type picked by hand
Senders send born-digital PDFs where possibleYour suppliers and scannersScans cannot be classified
The speech-to-text service is runningOperationsRecordings fail to transcribe
Source URLs are kept secretWhoever configures agentsAnyone holding one can push files into your inbox

7. Downstream​

When…Then
An item is convertedA draft document exists with the file attached; the row points at it for good
A source is revokedIts agent's next push is refused; captured items stay
An item is discardedThe stored file is deleted; the row remains

8. Don't confuse this with…​

AttachmentsFiles on an existing document. Capture creates a new one
Briefcase importA structured document from another Orbit environment
Intake formsDocuments from form submissions, no file involved
Zonal extractionReads fixed regions of a standard form on a type

9. Troubleshooting​

SymptomCause
no text layer was found…The file is a scan or photo — upload a text-based PDF or a .txt capture
Up to 20 files at a timeSplit the batch
A recording failed to classifyNo discernible speech, or it exceeded the transcription timeout
The suggested type does not resolveNo active type has that code in this project
An automated source stoppedIt was revoked, or the agent's configuration broke — check Last ingest
A converted row cannot be discardedBy design