Document Detail

Every document in Talonic has a detail page with four views: Raw Extraction, Resolved Data, Processing Log, and Original File. The detail page is where you inspect individual extraction results, verify field accuracy, and debug processing issues. It serves as the single source of truth for everything the platform knows about a document, from raw AI output to resolved canonical fields.

The Raw Extraction tab is the most detailed view, showing every field the AI discovered along with its confidence score and the source text that the value was extracted from. Each field displays a maturity badge (Core, Proven, or Candidate) indicating how well-established that field is across your document corpus. Synthetic metadata fields like filename and source_file_path appear here too, with full confidence (1.0).

Classification Pills: Language, Region, and PII

The document header shows Language and Region as pills led by a flag. The language pill reads the detected ISO language code, and the region pill reads the jurisdiction as an upper-case ISO country code. An explicit region subtag wins over the language default, so a document detected as en-GB shows the British flag rather than the default one for English. When triage flagged personal data, a PII marker appears beside them. These signals come from the triage ingest stage, and routing rules and access rules can read the same values.

The Documents list uses the same facts in its Classification column. Each row reads the document type first, then the jurisdiction (for example DE), the language (for example de), and PII when the row is flagged. Sensitivity and department fold into a +N pill whose tooltip names them, so long classification strings do not push the column around. The Status column is a single coloured dot (green done, amber partial, pulsing purple processing, gray queued, red failed), and hovering it shows the legend with the row's status named.

The Resolved Data tab shows how raw extracted fields map to your canonical field registry. Fields that matched automatically (similarity >= 0.80) display their canonical name and cluster. Fields in the confirm band (0.50-0.79) are flagged for review. This view helps you understand how the platform is normalizing field names across different document types and formats.

The Processing Log tab provides a stage-by-stage timeline of how the document was processed, including per-stage timing. You can see exactly how long OCR, classification, and extraction took, which is useful for diagnosing slow processing or understanding why a document was classified a particular way. The Original File tab lets you view or download the source file, so you can always compare the AI's extraction against the original document.

When reviewing extraction quality, start with the Raw Extraction tab to check that the AI found all expected fields. Compare the confidence scores across fields — values above 0.90 are typically reliable, while values below 0.70 may warrant manual verification. If a field is missing, check the Original File tab to confirm the information exists in the source document. The Processing Log tab can reveal whether the document was split into chunks, which sometimes causes fields near chunk boundaries to be missed.

Accessing Document Details via API

The document detail information visible in the UI is fully accessible through the REST API. You can retrieve a document's extraction results, download the OCR markdown, and inspect the processing metadata programmatically. This is particularly useful for building quality assurance workflows where you need to verify extraction results across hundreds of documents without clicking through each one manually.

curl https://api.talonic.com/v1/documents/doc_7f3a1b2c/fields \
  -H "Authorization: Bearer $TALONIC_API_KEY"

{
  "document_id": "doc_7f3a1b2c",
  "data": [
    {
      "field_id": "fld_1a2b3c",
      "canonical_name": "invoice_number",
      "tier": 1,
      "value": "INV-2026-0472",
      "confidence": 0.98
    },
    {
      "field_id": "fld_4d5e6f",
      "canonical_name": "total_amount",
      "tier": 1,
      "value": "4,250.00",
      "confidence": 0.95
    }
  ]
}

The fields response includes every captured field bound into the Field Registry, one row per occurrence, with its canonical concept, maturity level (the numeric tier: 1 = Core, 2 = Proven, 3 = Candidate), value, and confidence score. Fields with confidence below 0.70 typically warrant manual review, while fields above 0.90 are highly reliable. You can use this data to build automated validation rules: for example, flagging documents where critical fields like invoice_number or total_amount have low confidence scores and routing them to a human reviewer.

The document detail page also provides access to the OCR-generated markdown through both the UI and the API. This markdown representation preserves the document's structure — headings, tables, lists, and paragraphs — in a machine-readable format. Comparing the markdown against the extracted fields is a useful debugging technique: if a field is missing from the extraction, check whether the value appears in the markdown. If it does, the extraction model may need a master instruction to guide it to the right location. If it does not, the OCR stage may have missed the content, which can happen with low-resolution scans or complex layouts.