Reviewing Results

The job detail page provides: a progress bar with fill rate, a phase timeline, the strategy panel (Planner actions), a filter bar (Show All / Clean / Flagged), and CSV export (clean or full with metadata). The strategy yield breakdown shows how cells were distributed across resolution methods — registry transfer, raw extraction mapping, lookup cascade, deterministic compute, LLM extract, and bypass — giving you a clear picture of extraction efficiency for each run.

Start your review by switching to the Flagged filter to focus on cells that need attention — these are values with validation warnings, low confidence, or format mismatches. Click any cell to see its full provenance, including which phase produced it and the reasoning trace. Once you are satisfied, export via CSV — choose the clean export for downstream systems or the full export with metadata for auditing.

The colored dots on each cell are your quickest visual indicator of data quality. Blue dots indicate graph matches from Phase 1 (highest reliability), purple dots indicate computed values, teal dots indicate Planner transfers, indigo dots indicate AI extractions, and amber dots indicate lookup results or format flags. A grid dominated by blue and purple dots typically requires minimal review, while one with many indigo and amber dots may need more attention.

For large jobs with hundreds of documents, use a systematic review workflow: first address all Flagged rows, then spot-check a random sample of Clean rows to build confidence in the overall quality. If you find recurring errors in a specific field, consider updating the schema field's instruction or reference table, then run a new job — corrections you apply also feed back as training signals for future runs.

curl -s https://api.talonic.com/v1/jobs/c3d4e5f6-a7b8-9012-cdef-123456789012/results \
  -H "Authorization: Bearer $TALONIC_API_KEY"

# Response: one row per document
# {
#   "job_id": "c3d4e5f6-a7b8-9012-cdef-123456789012",
#   "job_status": "complete",
#   "schema": { "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901", "name": "Invoice Schema" },
#   "total_rows": 3,
#   "data": [
#     {
#       "document_id": "f0e1d2c3-b4a5-9687-8765-432109876543",
#       "filename": "Invoice_ACME_2025.pdf",
#       "status": "completed",
#       "values": {
#         "invoice_number": "INV-2025-0042",
#         "total_amount": "12450.00"
#       },
#       "confidence": 0.91,
#       "validation_flags": []
#     }
#   ]
# }

The API returns extracted values with a row-level confidence score and any validation flags per document. Per-cell provenance (the resolution type, Job phase, and reasoning trace behind each value) lives in the results grid: click any cell to open its provenance panel, or use the full CSV export, which includes a metadata column set for every field.

The strategy yield breakdown on the job detail page gives you an at-a-glance view of extraction efficiency. A high percentage of registry_transfer and deterministic_compute cells means your Field Registry is mature and Phase 1 is doing most of the work at zero AI cost. A high percentage of llm_extract cells suggests opportunities to improve — add more documents to grow the registry, refine reference tables for better lookup coverage, or add bypass strategies for fields with predictable values. Tracking strategy yield across multiple jobs over time is the best way to measure whether your Jobs are becoming more efficient.