Talonic

Name: Talonic
Author: Talonic GmbH

AgentA2A

The schema layer for enterprise data. Talonic extracts structured data from documents (PDF, DOCX, XLSX, scans, emails), validates against schemas, resolves entities into cases, and delivers workflow-ready data to systems of record. Supports 529 document types, 25+ file formats, per-cell provenance,…

by Talonic GmbHhomepage ↗v1.0.0

Observed by Wellknown

Evidence

Everything here was measured by our prober or read from a registry. Nothing is self-reported.

30-day availabilityno checks in window

30 days agotoday

Declared by sources

What the publisher says

Attributed to the source that supplied each field. Treated as claims, not facts.

document-extractionocrpdf-parsingdata-extractionschema-validationenterprise-documentsdocument-searchfield-registrydata-querystructured-dataenterprise-searchschema-managementdata-modelingfield-definitionsdata-deliverywebhookerp-integrationdata-pipelineworkflow-automationfree-toolspdf-conversion

Derived by Wellknown

Capabilities

Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.

documents.extractionData Extraction100%documents.conversionDocument Conversion100%data.databaseDatabases100%documents.ocrOCRdeclared communication.notificationsNotificationsdeclared automation.workflowsWorkflow Automation75%

Provenance

Where this record came from

Every source is kept verbatim. Field changes are logged as events.

A2A Agent Cardhttps://talonic.com/.well-known/agent.json

first seen 43 min ago · fetched 43 min agoopen ↗

Field history (7 recent events)

43 min ago · declared · summary → "The schema layer for enterprise data. Talonic extracts structured data from documents (PDF, DOCX, XLSX, scans, emails),
43 min ago · declared · description → "The schema layer for enterprise data. Talonic extracts structured data from documents (PDF, DOCX, XLSX, scans, emails),
43 min ago · declared · publisherName → "Talonic GmbH"
43 min ago · declared · publisherUrl → "https://talonic.com"
43 min ago · declared · homepageUrl → "https://talonic.com/docs"
43 min ago · declared · version → "1.0.0"
43 min ago · declared · protocols → ["a2a"]

Declared skills

Document Extraction — Extract structured data from any document. Send a file (PDF, DOCX, XLSX, image, scan, email) and receive schema-validated fields with confidence scores, provenance, and reasoning traces. Supports sync, async, and streaming modes.
Registry Query — Query previously ingested documents by field values without re-extraction. Filter, search, and materialize data from the field registry. Zero AI calls, zero cost for registry-resolved fields.
Schema Management — Create, update, version, and publish extraction schemas. Define field types, validation rules, format constraints, and delivery mappings. Supports JSON Schema, simplified fields, and flat key-type formats.
Data Delivery — Configure delivery bindings to route extracted data to systems of record. Supports webhooks (HMAC-SHA256), S3, SFTP, Google Sheets, email, and REST endpoints. Includes retry ladders, dead-letter queues, and replay capability.
Free Document Tools — Free browser-based tools at https://talonic.com/tools that demonstrate the Talonic engine. No signup required. Each tool extracts or converts a specific document type: PDF to Markdown, Invoice to CSV, Bank Statement to CSV, Bill of Lading, Certificate of Insurance, Contract, Receipt, Resume, Table Extractor, Handwriting to Text, and an Org Chart Builder.