Getting Started

Getting started with Talonic takes three steps: upload documents, compose a Spec, and run it as a Pipeline. Everything is reachable from the sidebar, which is a flat set of items: Documents to ingest and browse what arrived, Registry to explore the field registry, Spec to configure, Pipelines for pipeline runs, Products to deliver, and Apps for decision apps over your data. (Matching exists as an additional item, but it is gated behind advanced mode, Talonic staff membership, and dev builds, so it does not appear in a normal workspace.) Sources is not a sidebar item: open the Documents page and use the Sources button in its header to manage connectors. Most users see their first structured output within minutes of uploading.

Documents is where documents enter the system: through manual upload, connected cloud storage, email inboxes, or the API. The page has two tabs — Documents for everything that arrived, and Reference Data (?tab=reference-data) for the lookup tables matching and resolution check against — and its header carries the Sources button that opens connector management plus a Batches action for deferred processing. The Documents sidebar entry also shows a numeric badge whenever document-type detections are waiting for your confirmation. Spec (/specs) is where you compose a pipeline over a schema, and Pipelines (/pipelines) is where those pipeline runs appear, including the review queue where held fields are approved. Products is where approved data is delivered to downstream systems through configured bindings. For a fast single-document run, open the Extract slide-over with Cmd+J or from the in-page entry points.

For teams processing documents at scale, the recommended approach is to start with a small representative sample. Upload 5-10 documents of the same type, let the platform extract and classify them, then review the auto-generated schema. This lets you validate the output structure before committing to a large batch. Once the schema looks right, you can upload hundreds or thousands of documents and the knowledge graph will handle an increasing share of cells through instant graph matches.

The platform includes powerful keyboard shortcuts for fast navigation. Press Cmd+K (or Ctrl+K on Windows) to open Omnisearch, which lets you find documents, schemas, jobs, and fields from anywhere. Press Cmd+I to open the AI Agent for natural language queries about your workspace. The sidebar can be collapsed to give more screen real estate when reviewing extraction results.

If you plan to integrate Talonic into an existing data pipeline, start by creating an API key from Settings → API Keys. The REST API mirrors every action available in the web interface, so you can upload documents, retrieve extraction results, create schemas, and configure delivery bindings programmatically. Many teams begin with the UI for initial exploration and then transition to API-driven workflows as their integration matures.

1. Upload a few sample documents on the Documents page (drag and drop, or connect a source via the Sources header button).
2. Wait for extraction to complete — documents are OCR'd, classified, and fields are extracted automatically.
3. Open Spec (/specs) and compose a pipeline over a schema, or review the auto-generated schema first.
4. Run or preview the Spec to compile a Pipeline, visible in Pipelines (/pipelines). For a quick one-off, use Extract (Cmd+J).
5. Review held fields in the pipeline review queue and inspect the run — each cell shows confidence, provenance, and reasoning.

Getting Started with the API

If you prefer to integrate programmatically, the REST API lets you upload documents, retrieve results, and manage schemas without the web interface. Start by creating an API key from Settings, then use the extract endpoint to submit your first document. The response includes extraction status that you can poll until processing completes, or configure a webhook to receive a notification automatically when results are ready.

curl -X POST https://api.talonic.com/v1/sources/src_abc123/documents \
  -H "Authorization: Bearer $TALONIC_API_KEY" \
  -F "file=@contract.pdf"

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

{
  "id": "doc_7f3a1b2c",
  "filename": "contract.pdf",
  "status": "completed",
  "type_detected": "Employment Contract",
  "extraction_count": 1,
  "created_at": "2026-05-07T10:30:00Z"
}

Once you are comfortable with single-document extraction, explore batch processing for high-volume workloads. Set processing_mode=batch when uploading to defer AI extraction and run at 50% cost with a 48-hour delivery window. This is ideal for historical backlogs where immediate results are not required. You can monitor batch progress from the Batches page (the Batches action in the Documents page header) or poll the batch status endpoint via the API.