@talonic/docs 0.20.4 → 0.20.6

package/dist/content.js

@@ -1590,7 +1590,7 @@ var sections5 = [
       },
       {
         type: "callout",
-        text: "For the complete JSON Schema specification with all features, see the [Full Schema Reference](/docs#schema-reference) in the API docs."
+        text: "For the complete JSON Schema specification with all features, see the [Full Schema Reference](/docs/platform/schema-features) in the Platform Guide."
       }
     ],
     related: [

package/dist/index.d.ts

@@ -156,7 +156,7 @@ declare const PLATFORM_FAQ: {
     question: string;
     answer: string;
 }[];
-declare const LLMS_TXT = "# Talonic\n\n> AI-powered document structuring platform that turns unstructured files into schema-validated, provenance-tracked structured data.\n\nTalonic ingests documents in 25+ formats (PDFs, scans, images, spreadsheets, emails, archives), discovers every data field through AI extraction and semantic clustering, and produces structured datasets with per-cell confidence scores, reasoning traces, and source provenance. It runs a single deployable stack with Postgres + pgvector, Anthropic Claude for extraction, and Mistral Document AI for OCR.\n\n## How It Works\n\n1. **Upload** \u2014 Drag files/folders into Inputs or ingest via API. ZIP archives unpack automatically. Files are deduplicated via SHA-256 hashing.\n2. **Extract** \u2014 Each document goes through Document AI OCR (converts to Markdown), classification against a 529-type ontology, and AI field extraction (discovers every data point with confidence and source text).\n3. **Build Schema** \u2014 Extracted fields resolve into the Field Registry (canonical names, semantic clusters, master instructions). Define a user template selecting the fields you need.\n4. **Run Job** \u2014 A 4-phase pipeline fills every cell in a documents \u00D7 fields grid. ~30% filled instantly from graph matches, ~70% from AI agents.\n5. **Deliver** \u2014 Push approved data to webhooks, REST APIs, SFTP, email, or S3/R2 cloud storage.\n\n## Sources & Documents\n\nSupported formats across three processing paths:\n- **Text fast-path** (direct read): TXT, MD, HTML, XML, JSON, EML, CSV\n- **AI Vision** (multimodal): PNG, JPG, JPEG, GIF, WEBP\n- **OCR** (Mistral Document AI \u2192 Markdown): PDF, DOCX, DOC, PPTX, PPT, XLSX, XLS, XLSM, MSG, BMP\n- **Archives**: ZIP (recursive unpack)\n\nUpload methods: drag-and-drop UI, folder upload (preserves file paths), API upload (single, batch up to 200 files, or archive up to 500 MB). Batch mode available at 50% cost with 48-hour delivery window.\n\nEvery document is classified into a canonical type from the 529-type ontology (e.g., \"Employment Contract\", \"Invoice\", \"Bill of Lading\"). Classification is language-agnostic \u2014 a German Arbeitsvertrag maps to the same type as an English Employment Contract. Unresolvable documents get \"Unclassified Document\".\n\nDocument detail tabs: Raw Extraction (every field with confidence), Resolved Data (mapped to registry), Processing Log (per-stage timing), Original File.\n\n## Field Registry\n\nThe unified knowledge graph of all canonical fields, growing smarter with every document processed.\n\n- **Tier 1 (Core)**: Universal fields across many document types. Most reliable.\n- **Tier 2 (Established)**: Promoted from Tier 3 after frequency thresholds. Production-ready.\n- **Tier 3 (Emerging)**: Newly discovered from a few documents. May promote as more data arrives.\n\nFields with similar meanings cluster automatically via AI embeddings (e.g., \"Vendor Name\", \"Supplier Name\", \"Company Name\" \u2192 same cluster). Master instructions are AI-synthesized extraction directives that improve accuracy over time.\n\n## Schemas\n\nTwo types: **Generated schemas** (auto-created per document type from Tier 1+2 fields) and **User templates** (user-defined output structures).\n\nTemplate workflow: name it \u2192 add fields (display name, data type, extraction instructions) \u2192 map to registry (exact/semantic/composite matching) \u2192 add reference tables \u2192 publish an immutable version.\n\nField features: format constraints (regex validation with empty/flag/constant fallback), modifiers (date/number format, alias mapping, max_length), bypass strategies (constant, generator, reference lookup \u2014 skip LLM), capture submoves (match \u2192 compute \u2192 reason), output name remapping.\n\nVersioning: Live (published, read-only), Workshop (mutable draft), Version History (timeline with diff). Test extraction compares draft vs. live results before publishing.\n\n## Extraction Jobs (Runs)\n\nA job applies a schema to documents, producing a grid (rows = documents, columns = fields). Navigate to Structuring \u2192 Runs \u2192 New.\n\n**4-phase pipeline:**\n1. **Resolve** \u2014 ~30% of cells in seconds. Graph matches, fuzzy name matching, concept-synonym expansion, 3-tier reference lookup (normalize \u2192 fuzzy \u2192 AI), description scan. No AI calls (except rare Haiku fallback). Values normalized: dates \u2192 YYYY/MM/DD, numbers \u2192 2 decimal places.\n2. **Agent** \u2014 AI reviews gap patterns and produces typed strategy per field: compute (formula from grid values), transfer (copy from equivalent field), extract (re-read document with instructions, 5 concurrent), skip (with reasoning). Fields with manual instructions are always extracted, never skipped.\n3. **Validation** \u2014 Cross-field sanity checks: date_sanity, amount_mismatch, lookup_failed, low_confidence_outlier, unexpected_empty. Flags are informational only \u2014 never block output.\n4. **Re-read** \u2014 Context-aware gap filling. For each empty/low-confidence cell, AI re-reads the original document with field instruction + full grid context. Respects the confidence gate: cells \u2265 0.7 confidence are permanently protected.\n\nPer-cell provenance: confidence (0.0\u20131.0), resolution_type (graph_match | agent_derived | source_reread | unresolved), phase (1\u20134), reasoning trace, source reference (document, page, field).\n\n## Cases & Document Linking\n\nRegistry fields can be link keys: Identity (company/person names), Transaction (contract/PO/invoice numbers), Reference (project codes, cost centers). The linking pipeline normalizes values and builds a bipartite graph of documents \u2194 entities.\n\nA **case** = 2+ documents connected through transaction/reference entities. An **entity group** = 2+ documents connected through identity-only entities. High-frequency entities (>30% of documents) are auto-excluded from case formation.\n\nCase detail: documents, shared entities, evidence chain, timeline, AI-generated narration. Document Graph provides a D3-force visual layout. Case templates auto-discovered after 3+ cases form.\n\n## Smart Matching\n\nUpload CSV/Excel as reference datasets. Define field-to-field comparisons with weighted strategies: exact (case-insensitive), fuzzy (token-based with similarity threshold), date_range (configurable tolerance), numeric_range (percentage or absolute tolerance). AI can auto-suggest field mappings.\n\nResults: top 5 candidates per document with confidence scores and per-field evidence breakdown.\n\n## Validation & Quality\n\n- **Validation checks**: Schema-level rules (field format, value range, cross-field consistency, AI-proposed coherence). Run during Phase 3.\n- **Golden samples**: Manually-created reference datasets. Benchmark runs compare extraction vs. golden for per-field accuracy with AI judge verdicts.\n- **Approval gates**: Threshold-based auto-approve/flag (minimum confidence, validation pass rate, field coverage). Failed rows go to manual review queue.\n\n## Delivery\n\nDestinations: Webhook (HMAC-SHA256 signed), REST API (configurable headers), SFTP, Email (attachments), S3/R2 (cloud storage).\n\nField mappings transform output fields to match destination format. Triggers: auto on approval (stage/push), scheduled (cron), or manual. Failed exports retry with exponential backoff.\n\nDialects control serialization: date_format, number_locale, CSV delimiter, null representation, boolean format, encoding (UTF-8, UTF-8-BOM, ISO-8859-1).\n\n## Search & Navigation\n\n**Omnisearch** (Cmd+K / Ctrl+K): searches across documents, extracted values, field names, schema names, and sources simultaneously.\n\nDocument filters: field-value conditions with autocomplete, comparison operators (eq, contains, gt, between, is_empty), combinable. URL-serializable and saveable as presets.\n\nKeyboard shortcuts: Cmd+K (search), Cmd+J (quick extract), Escape (close overlays).\n\n## Team & Settings\n\n4 roles: Viewer (read-only), Member (full CRUD), Admin (+ team management), Owner (+ billing, API keys, org settings). New members auto-match by email domain with pending approval.\n\nUsage & Registry: per-feature cost breakdown, daily cost chart, call log with model/tokens/cost. Admin master view for cross-tenant stats.\n\n## API\n\nBase URL: `https://api.talonic.com`. Auth: `Authorization: Bearer tlnc_...` (SHA-256 hashed, shown once at creation). Scopes: extract, read, write.\n\nKey endpoints:\n- POST /v1/extract \u2014 Synchronous/async document extraction (`include_markdown=true` returns OCR text, `processing_mode=batch` for 50% cost)\n- GET /v1/documents \u2014 List with cursor pagination; GET /v1/documents/:id/markdown for OCR text\n- GET /v1/extractions \u2014 Query results and field corrections\n- POST /v1/schemas \u2014 Create/manage extraction schemas\n- GET /v1/jobs \u2014 Track async jobs and results; N-Shot comparisons, overrides, judge decisions\n- POST /v1/sources \u2014 Manage API sources and document ingest\n- POST /v1/webhooks \u2014 Configure webhook endpoints\n- /v1/resolutions \u2014 Resolution runs: list, create, get, execute, delete, results\n- /v1/linking \u2014 Link keys, document links, entity graph, classify, backfill, document-case map\n- /v1/schema-graph \u2014 Schema classes, versions, diffs (approve/reject), edges, aliases, visualize\n- /v1/structuring \u2014 Validation checks CRUD, approval gates CRUD with rules, result checks, pending approvals, approve/reject, delivery trigger\n- /v1/telemetry \u2014 Per-schema and per-run summaries, trends, field-level breakdowns\n- /v1/validation \u2014 Golden samples (list, get, delete), validation runs (list, create, get, delete, results)\n- /v1/credits \u2014 Balance, history, usage summary, daily usage, per-request usage log\n- /v1/cases \u2014 Status updates, edges, edge confirm/reject, split/merge, completeness, pin/remove documents\n- /v1/batches \u2014 Sync with provider, cancel\n- /v1/matching \u2014 Smart run, AI resolve, strategies CRUD, run results/progress, review\n- /v1/review \u2014 Assign, stats\n- /v1/quality \u2014 Ground truth entries CRUD, benchmark results, benchmark comparison\n- /v1/reference-data \u2014 JSON upload (POST create)\n\nWebhook events: extraction.completed, job.completed, export.completed, validation.completed. All HMAC-SHA256 signed with retry on failure.\n\n## Agent\n\nThe embedded AI assistant accessible from any page. Two modes:\n- **Chat mode** \u2014 Ask questions about the platform, your documents, extraction results, schemas, or workflows. Grounded in platform documentation.\n- **Planning mode** \u2014 Request actions (create schemas, run jobs, configure exports). The agent builds a plan, confirms with you, then executes.\n\nDocument upload flow: Cmd+J or the upload button opens quick extract. Drop a file, select a schema (or let AI discover fields), and get structured results.\n\n## Documentation\n\n- [API Documentation](https://talonic.com/docs): Complete REST API reference\n- [Platform Guide](https://talonic.com/docs/platform): Product documentation and feature guide\n- [OpenAPI Spec](https://talonic.com/docs/openapi.json): Machine-readable API specification\n";
+declare const LLMS_TXT = "# Talonic\n\n> The data registry for unstructured documents. Agents extract once, query forever. 529 document types, 25+ file formats, per-cell provenance. Co-author of DIN SPEC 91491.\n\n## For Agents\n\n- [MCP Server](https://mcp.talonic.com/mcp): Hosted MCP endpoint \u2014 zero install, native Model Context Protocol\n- [MCP Setup Guide](https://talonic.com/docs/mcp): Claude Desktop, Cursor, Cline, Continue, Cowork configuration\n- [Cost Headers](https://talonic.com/developers#billing): X-Talonic-Cost-Credits and X-Talonic-Balance-Credits on every response\n- [Credit Balance & Runway](https://talonic.com/docs/api/credits): GET /v1/credits/balance \u2014 check remaining budget before calls\n- [Idempotency-Key](https://talonic.com/docs/api#idempotency): Safe retries \u2014 pass Idempotency-Key header to deduplicate requests\n- [Auto Top-Up](https://talonic.com/developers#billing): Human-gated credit replenishment \u2014 agents can check, humans approve\n- [Sync/Async Contract](https://talonic.com/docs/api/extract): \u22645 pages \u2192 200 sync response; larger \u2192 202 with poll_url\n\n## Three Modes\n\n- [Mode 1 \u2014 Extract Everything](https://talonic.com/developers#trio): POST /v1/extract with no schema \u2014 discover all fields in any document\n- [Mode 2 \u2014 Extract a Shape](https://talonic.com/developers#trio): POST /v1/extract with a schema \u2014 get exactly the fields you define\n- [Mode 3 \u2014 Query Without Re-extracting](https://talonic.com/developers#trio): POST /v1/documents/filter \u2014 query the Field Registry across previously extracted documents\n\n## API Quickstart\n\n- [Getting Started](https://talonic.com/docs/getting-started): Authentication, first extraction, schema creation\n- [POST /v1/extract](https://talonic.com/docs/api/extract): Primary extraction endpoint \u2014 sync, async, and batch modes\n- [Documents](https://talonic.com/docs/api/documents): List, retrieve, delete documents and get markdown\n- [Extractions](https://talonic.com/docs/api/extractions): Query extraction results and submit corrections\n- [Schemas](https://talonic.com/docs/api/schemas): Create, update, list, and delete extraction schemas\n- [Jobs](https://talonic.com/docs/api/jobs): Track async extraction jobs and results\n- [Webhooks](https://talonic.com/docs/api/webhooks): Event-driven flow \u2014 HMAC-SHA256 signed, exponential backoff retries\n- [Search & Filter](https://talonic.com/docs/api/search): Omnisearch, document filtering, field autocomplete\n- [OpenAPI 3.1 Spec](https://talonic.com/openapi.json): Machine-readable API specification\n\n## Concepts\n\n- [Field Registry](https://talonic.com/docs/concepts/field-registry): Unified knowledge graph of all extracted fields \u2014 tiers, clusters, master instructions\n- [Provenance & Confidence](https://talonic.com/docs/concepts/provenance): Per-cell confidence scores (0.0\u20131.0), resolution types, reasoning traces\n- [Cases & Document Linking](https://talonic.com/docs/concepts/cases): Entity matching, case formation, evidence chains\n- [4-Phase Pipeline](https://talonic.com/docs/concepts/pipeline): Resolve \u2192 Agent \u2192 Validation \u2192 Re-read\n- [Document Ontology](https://talonic.com/docs/concepts/ontology): 529-type classification across 10 categories\n- [Schemas](https://talonic.com/docs/concepts/schemas): Generated schemas vs. user templates, field matching, versioning\n\n## SDKs\n\n- [Node SDK](https://talonic.com/docs/sdk): Official Node.js/TypeScript SDK \u2014 extract, documents, schemas, jobs\n- [MCP Server Docs](https://talonic.com/docs/mcp): 7 tools \u2014 extract, search, filter, get_document, to_markdown, list_schemas, save_schema\n- [Authentication](https://talonic.com/docs/authentication): API key creation, scopes, Bearer token usage\n- [Error Codes](https://talonic.com/docs/errors): Error response format and code reference\n- [Rate Limits](https://talonic.com/docs/rate-limits): Rate limit tiers by plan and headers\n\n## Platform Guide\n\n- [Platform Overview](https://talonic.com/docs/platform): Core concepts, platform flow, supported formats\n- [Field Intelligence](https://talonic.com/docs/platform/tier-system): Tier system, semantic clusters, master instructions\n- [Schemas & Templates](https://talonic.com/docs/platform/generated-schemas): Schema creation, field matching, versioning, dialects\n- [Extraction Jobs](https://talonic.com/docs/platform/creating-job): Creating jobs, reviewing results, confidence and provenance\n- [Linking & Cases](https://talonic.com/docs/platform/entity-linking): Entity linking, link keys, cases, anomaly detection\n- [Validation & Quality](https://talonic.com/docs/platform/validation-checks): Golden samples, approval gates, ground truth benchmarks\n- [Delivery](https://talonic.com/docs/platform/destinations): Webhooks, REST, SFTP, email, S3/R2, field mappings, triggers\n\n## Document Types\n\n- [Financial & Tax](https://talonic.com/document-types/financial-tax): Schedule K-1, VAT Returns, Balance Sheets, SWIFT MT103, and 49 more\n- [Procurement & Invoicing](https://talonic.com/document-types/procurement-invoicing): Purchase Orders, Commercial Invoices, RFPs, and 50 more\n- [Trade & Logistics](https://talonic.com/document-types/trade-logistics): Bills of Lading, Air Waybills, Customs Declarations, and 50 more\n- [Legal & Contracts](https://talonic.com/document-types/legal-contracts): NDAs, MSAs, Loan Agreements, DPAs, and 48 more\n- [Corporate & Governance](https://talonic.com/document-types/corporate-governance): KYC Packages, Board Resolutions, ESG Reports, and 50 more\n- [Healthcare & Life Sciences](https://talonic.com/document-types/healthcare-life-sciences): Discharge Summaries, Clinical Trials, 510(k), and 50 more\n- [Manufacturing & Quality](https://talonic.com/document-types/manufacturing-quality): Certificates of Analysis, FMEA, BOM, PPAP, and 49 more\n- [Insurance & Claims](https://talonic.com/document-types/insurance-claims): FNOL Reports, Policy Declarations, Reinsurance, and 50 more\n- [Real Estate & Construction](https://talonic.com/document-types/real-estate-construction): Property Deeds, AIA G702, Lien Waivers, and 50 more\n- [HR & Employee Records](https://talonic.com/document-types/hr-employee-records): I-9 Forms, FMLA Certifications, Payroll Registers, and 49 more\n\n## Company\n\n- [Product](https://talonic.com/product): Full platform walkthrough for technical evaluation\n- [Pricing](https://talonic.com/pricing): Free (5,000 credits/mo), Pro (\u20AC49/mo), Enterprise (custom)\n- [Developers](https://talonic.com/developers): Three Modes, API, SDK, MCP server overview\n- [DIN SPEC 91491](https://talonic.com/din-91491): Europe's first standard for AI-ready data\n- [Security](https://talonic.com/security): GDPR, HIPAA, ISO 27001, ISO 42001, EU data residency\n- [Contact](https://talonic.com/contact): Book a demo or request a schema audit\n\n## Optional\n\n- [Full Documentation for AI Models](https://talonic.com/llms-full.txt): Concatenated full reference \u2014 API, platform, pricing, compliance\n- [Talonic vs Reducto](https://talonic.com/vs/reducto): Schema-first vs. parse-first comparison\n- [Talonic vs Instabase](https://talonic.com/vs/instabase): Platform architecture comparison\n";
 declare const LLMS_FULL_TXT_HEADER = "# Talonic \u2014 Full Documentation\n\n> This file contains the complete Talonic documentation for LLM consumption.\n> For a summary, see llms.txt.\n\n";
 
 export { API_FAQ, API_NAV_SECTIONS, API_SECTION_META, ApiReference, Callout, CellDot, CodeBlock, DownloadMarkdown, EndpointBlock, type HttpMethod, InlineCode, LLMS_FULL_TXT_HEADER, LLMS_TXT, type LinkComponent, MCP_FAQ, MCP_NAV_SECTIONS, MCP_SECTION_META, MethodBadge, MockNavItem, type NavSection, P, PLATFORM_FAQ, PLATFORM_NAV_SECTIONS, PLATFORM_SECTION_META, type Param, ParamTable, PipelineConnector, PipelineStage, PlatformGuide, SDK_FAQ, SDK_NAV_SECTIONS, SDK_SECTION_META, SectionHeading, type SectionMeta, Sidebar, SubHeading, TierBadge, UiExcerpt, highlightJson };

package/dist/index.js

@@ -5615,8 +5615,8 @@ function PlatformGuide({ LinkComponent }) {
       /* @__PURE__ */ jsxs6(Callout, { children: [
         "For the complete JSON Schema specification with all features, see the",
         " ",
-        /* @__PURE__ */ jsx6(LinkComp, { href: "/docs#schema-reference", children: "Full Schema Reference" }),
-        " in the API docs. A downloadable template is available in the",
+        /* @__PURE__ */ jsx6(LinkComp, { href: "/docs/platform/schema-features", children: "Full Schema Reference" }),
+        " in the Platform Guide. A downloadable template is available in the",
         " ",
         /* @__PURE__ */ jsx6(LinkComp, { href: "https://github.com/talonicdev/platform/blob/main/packages/docs/src/schema-template.json", children: "repository" }),
         "."
@@ -6843,147 +6843,90 @@ var PLATFORM_FAQ = [
 ];
 var LLMS_TXT = `# Talonic
 
-> AI-powered document structuring platform that turns unstructured files into schema-validated, provenance-tracked structured data.
+> The data registry for unstructured documents. Agents extract once, query forever. 529 document types, 25+ file formats, per-cell provenance. Co-author of DIN SPEC 91491.
 
-Talonic ingests documents in 25+ formats (PDFs, scans, images, spreadsheets, emails, archives), discovers every data field through AI extraction and semantic clustering, and produces structured datasets with per-cell confidence scores, reasoning traces, and source provenance. It runs a single deployable stack with Postgres + pgvector, Anthropic Claude for extraction, and Mistral Document AI for OCR.
+## For Agents
 
-## How It Works
+- [MCP Server](https://mcp.talonic.com/mcp): Hosted MCP endpoint \u2014 zero install, native Model Context Protocol
+- [MCP Setup Guide](https://talonic.com/docs/mcp): Claude Desktop, Cursor, Cline, Continue, Cowork configuration
+- [Cost Headers](https://talonic.com/developers#billing): X-Talonic-Cost-Credits and X-Talonic-Balance-Credits on every response
+- [Credit Balance & Runway](https://talonic.com/docs/api/credits): GET /v1/credits/balance \u2014 check remaining budget before calls
+- [Idempotency-Key](https://talonic.com/docs/api#idempotency): Safe retries \u2014 pass Idempotency-Key header to deduplicate requests
+- [Auto Top-Up](https://talonic.com/developers#billing): Human-gated credit replenishment \u2014 agents can check, humans approve
+- [Sync/Async Contract](https://talonic.com/docs/api/extract): \u22645 pages \u2192 200 sync response; larger \u2192 202 with poll_url
 
-1. **Upload** \u2014 Drag files/folders into Inputs or ingest via API. ZIP archives unpack automatically. Files are deduplicated via SHA-256 hashing.
-2. **Extract** \u2014 Each document goes through Document AI OCR (converts to Markdown), classification against a 529-type ontology, and AI field extraction (discovers every data point with confidence and source text).
-3. **Build Schema** \u2014 Extracted fields resolve into the Field Registry (canonical names, semantic clusters, master instructions). Define a user template selecting the fields you need.
-4. **Run Job** \u2014 A 4-phase pipeline fills every cell in a documents \xD7 fields grid. ~30% filled instantly from graph matches, ~70% from AI agents.
-5. **Deliver** \u2014 Push approved data to webhooks, REST APIs, SFTP, email, or S3/R2 cloud storage.
+## Three Modes
 
-## Sources & Documents
+- [Mode 1 \u2014 Extract Everything](https://talonic.com/developers#trio): POST /v1/extract with no schema \u2014 discover all fields in any document
+- [Mode 2 \u2014 Extract a Shape](https://talonic.com/developers#trio): POST /v1/extract with a schema \u2014 get exactly the fields you define
+- [Mode 3 \u2014 Query Without Re-extracting](https://talonic.com/developers#trio): POST /v1/documents/filter \u2014 query the Field Registry across previously extracted documents
 
-Supported formats across three processing paths:
-- **Text fast-path** (direct read): TXT, MD, HTML, XML, JSON, EML, CSV
-- **AI Vision** (multimodal): PNG, JPG, JPEG, GIF, WEBP
-- **OCR** (Mistral Document AI \u2192 Markdown): PDF, DOCX, DOC, PPTX, PPT, XLSX, XLS, XLSM, MSG, BMP
-- **Archives**: ZIP (recursive unpack)
+## API Quickstart
 
-Upload methods: drag-and-drop UI, folder upload (preserves file paths), API upload (single, batch up to 200 files, or archive up to 500 MB). Batch mode available at 50% cost with 48-hour delivery window.
+- [Getting Started](https://talonic.com/docs/getting-started): Authentication, first extraction, schema creation
+- [POST /v1/extract](https://talonic.com/docs/api/extract): Primary extraction endpoint \u2014 sync, async, and batch modes
+- [Documents](https://talonic.com/docs/api/documents): List, retrieve, delete documents and get markdown
+- [Extractions](https://talonic.com/docs/api/extractions): Query extraction results and submit corrections
+- [Schemas](https://talonic.com/docs/api/schemas): Create, update, list, and delete extraction schemas
+- [Jobs](https://talonic.com/docs/api/jobs): Track async extraction jobs and results
+- [Webhooks](https://talonic.com/docs/api/webhooks): Event-driven flow \u2014 HMAC-SHA256 signed, exponential backoff retries
+- [Search & Filter](https://talonic.com/docs/api/search): Omnisearch, document filtering, field autocomplete
+- [OpenAPI 3.1 Spec](https://talonic.com/openapi.json): Machine-readable API specification
 
-Every document is classified into a canonical type from the 529-type ontology (e.g., "Employment Contract", "Invoice", "Bill of Lading"). Classification is language-agnostic \u2014 a German Arbeitsvertrag maps to the same type as an English Employment Contract. Unresolvable documents get "Unclassified Document".
+## Concepts
 
-Document detail tabs: Raw Extraction (every field with confidence), Resolved Data (mapped to registry), Processing Log (per-stage timing), Original File.
+- [Field Registry](https://talonic.com/docs/concepts/field-registry): Unified knowledge graph of all extracted fields \u2014 tiers, clusters, master instructions
+- [Provenance & Confidence](https://talonic.com/docs/concepts/provenance): Per-cell confidence scores (0.0\u20131.0), resolution types, reasoning traces
+- [Cases & Document Linking](https://talonic.com/docs/concepts/cases): Entity matching, case formation, evidence chains
+- [4-Phase Pipeline](https://talonic.com/docs/concepts/pipeline): Resolve \u2192 Agent \u2192 Validation \u2192 Re-read
+- [Document Ontology](https://talonic.com/docs/concepts/ontology): 529-type classification across 10 categories
+- [Schemas](https://talonic.com/docs/concepts/schemas): Generated schemas vs. user templates, field matching, versioning
 
-## Field Registry
+## SDKs
 
-The unified knowledge graph of all canonical fields, growing smarter with every document processed.
+- [Node SDK](https://talonic.com/docs/sdk): Official Node.js/TypeScript SDK \u2014 extract, documents, schemas, jobs
+- [MCP Server Docs](https://talonic.com/docs/mcp): 7 tools \u2014 extract, search, filter, get_document, to_markdown, list_schemas, save_schema
+- [Authentication](https://talonic.com/docs/authentication): API key creation, scopes, Bearer token usage
+- [Error Codes](https://talonic.com/docs/errors): Error response format and code reference
+- [Rate Limits](https://talonic.com/docs/rate-limits): Rate limit tiers by plan and headers
 
-- **Tier 1 (Core)**: Universal fields across many document types. Most reliable.
-- **Tier 2 (Established)**: Promoted from Tier 3 after frequency thresholds. Production-ready.
-- **Tier 3 (Emerging)**: Newly discovered from a few documents. May promote as more data arrives.
+## Platform Guide
 
-Fields with similar meanings cluster automatically via AI embeddings (e.g., "Vendor Name", "Supplier Name", "Company Name" \u2192 same cluster). Master instructions are AI-synthesized extraction directives that improve accuracy over time.
+- [Platform Overview](https://talonic.com/docs/platform): Core concepts, platform flow, supported formats
+- [Field Intelligence](https://talonic.com/docs/platform/tier-system): Tier system, semantic clusters, master instructions
+- [Schemas & Templates](https://talonic.com/docs/platform/generated-schemas): Schema creation, field matching, versioning, dialects
+- [Extraction Jobs](https://talonic.com/docs/platform/creating-job): Creating jobs, reviewing results, confidence and provenance
+- [Linking & Cases](https://talonic.com/docs/platform/entity-linking): Entity linking, link keys, cases, anomaly detection
+- [Validation & Quality](https://talonic.com/docs/platform/validation-checks): Golden samples, approval gates, ground truth benchmarks
+- [Delivery](https://talonic.com/docs/platform/destinations): Webhooks, REST, SFTP, email, S3/R2, field mappings, triggers
 
-## Schemas
+## Document Types
 
-Two types: **Generated schemas** (auto-created per document type from Tier 1+2 fields) and **User templates** (user-defined output structures).
+- [Financial & Tax](https://talonic.com/document-types/financial-tax): Schedule K-1, VAT Returns, Balance Sheets, SWIFT MT103, and 49 more
+- [Procurement & Invoicing](https://talonic.com/document-types/procurement-invoicing): Purchase Orders, Commercial Invoices, RFPs, and 50 more
+- [Trade & Logistics](https://talonic.com/document-types/trade-logistics): Bills of Lading, Air Waybills, Customs Declarations, and 50 more
+- [Legal & Contracts](https://talonic.com/document-types/legal-contracts): NDAs, MSAs, Loan Agreements, DPAs, and 48 more
+- [Corporate & Governance](https://talonic.com/document-types/corporate-governance): KYC Packages, Board Resolutions, ESG Reports, and 50 more
+- [Healthcare & Life Sciences](https://talonic.com/document-types/healthcare-life-sciences): Discharge Summaries, Clinical Trials, 510(k), and 50 more
+- [Manufacturing & Quality](https://talonic.com/document-types/manufacturing-quality): Certificates of Analysis, FMEA, BOM, PPAP, and 49 more
+- [Insurance & Claims](https://talonic.com/document-types/insurance-claims): FNOL Reports, Policy Declarations, Reinsurance, and 50 more
+- [Real Estate & Construction](https://talonic.com/document-types/real-estate-construction): Property Deeds, AIA G702, Lien Waivers, and 50 more
+- [HR & Employee Records](https://talonic.com/document-types/hr-employee-records): I-9 Forms, FMLA Certifications, Payroll Registers, and 49 more
 
-Template workflow: name it \u2192 add fields (display name, data type, extraction instructions) \u2192 map to registry (exact/semantic/composite matching) \u2192 add reference tables \u2192 publish an immutable version.
+## Company
 
-Field features: format constraints (regex validation with empty/flag/constant fallback), modifiers (date/number format, alias mapping, max_length), bypass strategies (constant, generator, reference lookup \u2014 skip LLM), capture submoves (match \u2192 compute \u2192 reason), output name remapping.
+- [Product](https://talonic.com/product): Full platform walkthrough for technical evaluation
+- [Pricing](https://talonic.com/pricing): Free (5,000 credits/mo), Pro (\u20AC49/mo), Enterprise (custom)
+- [Developers](https://talonic.com/developers): Three Modes, API, SDK, MCP server overview
+- [DIN SPEC 91491](https://talonic.com/din-91491): Europe's first standard for AI-ready data
+- [Security](https://talonic.com/security): GDPR, HIPAA, ISO 27001, ISO 42001, EU data residency
+- [Contact](https://talonic.com/contact): Book a demo or request a schema audit
 
-Versioning: Live (published, read-only), Workshop (mutable draft), Version History (timeline with diff). Test extraction compares draft vs. live results before publishing.
+## Optional
 
-## Extraction Jobs (Runs)
-
-A job applies a schema to documents, producing a grid (rows = documents, columns = fields). Navigate to Structuring \u2192 Runs \u2192 New.
-
-**4-phase pipeline:**
-1. **Resolve** \u2014 ~30% of cells in seconds. Graph matches, fuzzy name matching, concept-synonym expansion, 3-tier reference lookup (normalize \u2192 fuzzy \u2192 AI), description scan. No AI calls (except rare Haiku fallback). Values normalized: dates \u2192 YYYY/MM/DD, numbers \u2192 2 decimal places.
-2. **Agent** \u2014 AI reviews gap patterns and produces typed strategy per field: compute (formula from grid values), transfer (copy from equivalent field), extract (re-read document with instructions, 5 concurrent), skip (with reasoning). Fields with manual instructions are always extracted, never skipped.
-3. **Validation** \u2014 Cross-field sanity checks: date_sanity, amount_mismatch, lookup_failed, low_confidence_outlier, unexpected_empty. Flags are informational only \u2014 never block output.
-4. **Re-read** \u2014 Context-aware gap filling. For each empty/low-confidence cell, AI re-reads the original document with field instruction + full grid context. Respects the confidence gate: cells \u2265 0.7 confidence are permanently protected.
-
-Per-cell provenance: confidence (0.0\u20131.0), resolution_type (graph_match | agent_derived | source_reread | unresolved), phase (1\u20134), reasoning trace, source reference (document, page, field).
-
-## Cases & Document Linking
-
-Registry fields can be link keys: Identity (company/person names), Transaction (contract/PO/invoice numbers), Reference (project codes, cost centers). The linking pipeline normalizes values and builds a bipartite graph of documents \u2194 entities.
-
-A **case** = 2+ documents connected through transaction/reference entities. An **entity group** = 2+ documents connected through identity-only entities. High-frequency entities (>30% of documents) are auto-excluded from case formation.
-
-Case detail: documents, shared entities, evidence chain, timeline, AI-generated narration. Document Graph provides a D3-force visual layout. Case templates auto-discovered after 3+ cases form.
-
-## Smart Matching
-
-Upload CSV/Excel as reference datasets. Define field-to-field comparisons with weighted strategies: exact (case-insensitive), fuzzy (token-based with similarity threshold), date_range (configurable tolerance), numeric_range (percentage or absolute tolerance). AI can auto-suggest field mappings.
-
-Results: top 5 candidates per document with confidence scores and per-field evidence breakdown.
-
-## Validation & Quality
-
-- **Validation checks**: Schema-level rules (field format, value range, cross-field consistency, AI-proposed coherence). Run during Phase 3.
-- **Golden samples**: Manually-created reference datasets. Benchmark runs compare extraction vs. golden for per-field accuracy with AI judge verdicts.
-- **Approval gates**: Threshold-based auto-approve/flag (minimum confidence, validation pass rate, field coverage). Failed rows go to manual review queue.
-
-## Delivery
-
-Destinations: Webhook (HMAC-SHA256 signed), REST API (configurable headers), SFTP, Email (attachments), S3/R2 (cloud storage).
-
-Field mappings transform output fields to match destination format. Triggers: auto on approval (stage/push), scheduled (cron), or manual. Failed exports retry with exponential backoff.
-
-Dialects control serialization: date_format, number_locale, CSV delimiter, null representation, boolean format, encoding (UTF-8, UTF-8-BOM, ISO-8859-1).
-
-## Search & Navigation
-
-**Omnisearch** (Cmd+K / Ctrl+K): searches across documents, extracted values, field names, schema names, and sources simultaneously.
-
-Document filters: field-value conditions with autocomplete, comparison operators (eq, contains, gt, between, is_empty), combinable. URL-serializable and saveable as presets.
-
-Keyboard shortcuts: Cmd+K (search), Cmd+J (quick extract), Escape (close overlays).
-
-## Team & Settings
-
-4 roles: Viewer (read-only), Member (full CRUD), Admin (+ team management), Owner (+ billing, API keys, org settings). New members auto-match by email domain with pending approval.
-
-Usage & Registry: per-feature cost breakdown, daily cost chart, call log with model/tokens/cost. Admin master view for cross-tenant stats.
-
-## API
-
-Base URL: \`https://api.talonic.com\`. Auth: \`Authorization: Bearer tlnc_...\` (SHA-256 hashed, shown once at creation). Scopes: extract, read, write.
-
-Key endpoints:
-- POST /v1/extract \u2014 Synchronous/async document extraction (\`include_markdown=true\` returns OCR text, \`processing_mode=batch\` for 50% cost)
-- GET /v1/documents \u2014 List with cursor pagination; GET /v1/documents/:id/markdown for OCR text
-- GET /v1/extractions \u2014 Query results and field corrections
-- POST /v1/schemas \u2014 Create/manage extraction schemas
-- GET /v1/jobs \u2014 Track async jobs and results; N-Shot comparisons, overrides, judge decisions
-- POST /v1/sources \u2014 Manage API sources and document ingest
-- POST /v1/webhooks \u2014 Configure webhook endpoints
-- /v1/resolutions \u2014 Resolution runs: list, create, get, execute, delete, results
-- /v1/linking \u2014 Link keys, document links, entity graph, classify, backfill, document-case map
-- /v1/schema-graph \u2014 Schema classes, versions, diffs (approve/reject), edges, aliases, visualize
-- /v1/structuring \u2014 Validation checks CRUD, approval gates CRUD with rules, result checks, pending approvals, approve/reject, delivery trigger
-- /v1/telemetry \u2014 Per-schema and per-run summaries, trends, field-level breakdowns
-- /v1/validation \u2014 Golden samples (list, get, delete), validation runs (list, create, get, delete, results)
-- /v1/credits \u2014 Balance, history, usage summary, daily usage, per-request usage log
-- /v1/cases \u2014 Status updates, edges, edge confirm/reject, split/merge, completeness, pin/remove documents
-- /v1/batches \u2014 Sync with provider, cancel
-- /v1/matching \u2014 Smart run, AI resolve, strategies CRUD, run results/progress, review
-- /v1/review \u2014 Assign, stats
-- /v1/quality \u2014 Ground truth entries CRUD, benchmark results, benchmark comparison
-- /v1/reference-data \u2014 JSON upload (POST create)
-
-Webhook events: extraction.completed, job.completed, export.completed, validation.completed. All HMAC-SHA256 signed with retry on failure.
-
-## Agent
-
-The embedded AI assistant accessible from any page. Two modes:
-- **Chat mode** \u2014 Ask questions about the platform, your documents, extraction results, schemas, or workflows. Grounded in platform documentation.
-- **Planning mode** \u2014 Request actions (create schemas, run jobs, configure exports). The agent builds a plan, confirms with you, then executes.
-
-Document upload flow: Cmd+J or the upload button opens quick extract. Drop a file, select a schema (or let AI discover fields), and get structured results.
-
-## Documentation
-
-- [API Documentation](https://talonic.com/docs): Complete REST API reference
-- [Platform Guide](https://talonic.com/docs/platform): Product documentation and feature guide
-- [OpenAPI Spec](https://talonic.com/docs/openapi.json): Machine-readable API specification
+- [Full Documentation for AI Models](https://talonic.com/llms-full.txt): Concatenated full reference \u2014 API, platform, pricing, compliance
+- [Talonic vs Reducto](https://talonic.com/vs/reducto): Schema-first vs. parse-first comparison
+- [Talonic vs Instabase](https://talonic.com/vs/instabase): Platform architecture comparison
 `;
 var LLMS_FULL_TXT_HEADER = `# Talonic \u2014 Full Documentation