Accepting Design Partners

Enterprise Document
Management & AI.

Upload, organize, version, share, and annotate documents. Built-in AI search, compliance scanning, and OCR. Stable release arriving soon.

See Product Demo
Ask AI — Grounded answers with citations
CordonData + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity Recent Chats 💬 Project Phoenix launch plan 💬 Q3 revenue comparison 💬 HR policy review 💬 Contract clause search AM Alex Morgan alex.morgan@company.com Ask AI Workspace: Q3-Strategy ▼ In Project_Phoenix_Launch_Brief.pdf, what is theproject codename? ▾ Analyzed documents 🔍 Searched knowledge base for relevant information 📄 Found relevant content in Project_Phoenix_Launch_Brief.pdf ✅ Answer grounded in source documents I found the closest matching evidence for: In Project_Phoenix_Launch_Brief.pdf, what is the project codename? in Project_Phoenix_Launch_Brief.pdf. Relevant excerpt: Document: Project_Phoenix_Launch_Brief.pdf "Project Phoenix launches Q4 2026. Codename: PHOENIX-7. Target markets: APAC, EMEA, NA." This is the best available grounded result from the retrieved knowledge-base content. Would you like me to go deeper on any specific part? 1Project_Phoenix_Launch_Brief.pdf 📋 Copy ↻ Regenerate 👍 👎 💡 SUGGESTED FOLLOW-UPS 📅 When does Phoenix launch? 🎯 List target markets 👥 Show launch team Ask the knowledge base... 📎 🔍 Send ↑
CordonData + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity AM Alex Morgan alex.morgan@company.com My Uploads Workspace: My Library ▼ + New Folder Upload Share 🔍 Search files... NAMESTATUSSIZE 📁 Projects12 files 📁 Phoenix5 files 📄 Project_Phoenix_Launch_Brief.pdfOCR ✓AI ✓1.2 MB 📊 Phoenix_Budget_2026.xlsxOCR ✓AI ✓1.1 MB 📄 Vendor_Contract_Draft.docxProcessing856 KB 📄 Compliance_Policy_2026.pdfOCR ✓AI ✓3.2 MB 🏷️ TAGS #phoenix #q3 #launch #strategy + add VIEW ≡ List ▦ Grid ↕ Sort: A-Z ⭐ Starred 🔗 Share 📤 Uploading Phoenix_Marketing_Plan.pdf...78%
CordonData + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity AM Alex Morgan alex.morgan@company.com System Explorer Workspace: Q3-Strategy ▼ 📡 Connected 📁 Knowledge 📊 Activity Knowledge Base: Q3-Strategy ▼ + Connect source 📂 Folder Tree 📁 Q3-Strategy 📁 Projects 📄 Project_Phoenix_Launch_Brief.pdf 📄 Phoenix_Budget_2026.xlsx 📁 Policies 📄 HR_Manual.pdf 📁 Compliance 📁 Reports 📁 Templates 📁 Archive 47 folders • 1,280 docs 📄 Project_Phoenix_Launch_Brief.pdf Size: 2.4 MB Modified: 2 hours ago Status: ● AI Ready OCR: ● Complete Chunks: 47 Source: My Uploads Last editor: Alex Morgan Ask AI about this 📥 Save 🔗 Share 🛡️ Scan PII 🗑️ Move to trash Version history: 3 revisions 📊 SYNC THROUGHPUT (last 24h) 📥 Indexed: 142 docs ⏱ Avg latency: 2.3s 🔄 Synced: 38 sources 🛡️ Scanned: 142 (12 with findings) ❌ Failed: 0 📊 Queue: 2 pending 00:00 04:00 08:00 12:00 16:00 20:00
CordonData + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity AM Alex Morgan alex.morgan@company.com Compliance — PII / NHI / Secret Scanner PII FINDINGS25 NHI FINDINGS3 SECRETS3 CLEAN2 FILECATEGORYSCAN TIMEVIEW 📄 Employee_Records_Q3.pdfPII-12NHI-31.2s👁 View 📄 Project_Phoenix_Launch_Brief.pdfCLEAN0.8s👁 View 📄 Vendor_Contract_Draft.docxPII-50.9s👁 View 📄 Employee_Onboarding_Form.pdfPII-8SEC-21.4s👁 View 📄 Employee_Records_Q3.pdf — Redacted Preview (Safe to Share) Employee: [REDACTED — SSN] | Email: [REDACTED] Phone: [REDACTED — Phone] | Medical: [REDACTED — NHI/MRN] API key: [REDACTED — Secret] — safe to share 🔬 ACTIVE RULES SSN Regex Email/Phone NHI/MRN (ML) Entropy ≥ 4.5 IBAN+SWIFT +12 more
CordonData + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity AM Alex Morgan alex.morgan@company.com Activity Audit Range: Last 30 days ▼ ACTIVE USERS47 LOGINS1,247 CHATS328 RAG Qs412 All Users My Activity 🔍 Search users... USERLOGINSCHATSRAGDOCSAPPS AM Alex Morgan alex.morgan@company.com 170 41 23 9 3 A Auditor User auditor.user@company.com 43 2 2 0 1 M Maya Chen maya.chen@company.com 38 14 8 2 1 D David Park david.park@company.com 36 11 6 0 1 📈 ACTIVITY TIMELINE (7 days) MonTueWedThuFriSatSun ● Logins ● Chats Showing 4 of 47 active users • Total activity: 1,247 events ⏱ Avg session: 14m 22s  •  Top user: Alex Morgan 💰 Token usage: 2.4M  •  Cost: $187.42  •  Compliance scans: 36 (12 findings) 📥 Export CSV 📊 Open in BI
CordonData + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity AM Alex Morgan alex.morgan@company.com Global Search Scope: All KBs ▼ 🔍 project codename Search 💡 Operators: "phrase" AND OR -exclude field:value site:kb after:2025 All (47) 📄 PDF (12) 📊 XLSX (8) 📄 DOCX (15) 🖼️ IMG 📁 All KBs ▼ ⭐ Save search 3 documents matched across 2 sources • 0.18s Sort: Relevance ▼ 📄 Project_Phoenix_Launch_Brief.pdf My Library / Projects / Phoenix • PDF • 1.2 MB ...the project codename is PHOENIX-7. Launching Q4 2026 across APAC, EMEA, NA... 98% 📄 APAC_Launch_Strategy.pdf My Library / Projects / Phoenix • PDF • 1.8 MB Section 3.2 references the project codename and lists the codename mappings... 87% 📄 EMEA_Launch_Plan.docx Team Workspace DMS / Launch Plans • DOCX • 542 KB ...the EMEA project codename rollout schedule and stakeholder communications... 72% 💡 AI Summary Across 3 matched documents, the project codename appears in 4 contexts. Primary: PHOENIX-7 Open in Ask AI → 🕐 RECENT QUERIES 🔍 project codename • 47 results • 2m ago 🔍 "compliance policy" AND redacted • 12 results • 15m ago Rerun ↻ Rerun ↻
Live Demo

Your Documents, Supercharged

CordonData is a complete Document Management System — upload, organize, version, share, and annotate. Then layer on AI search, compliance scanning, and OCR to unlock everything inside your files.

Document Management

Upload up to 500MB per file. Organize with nested folders (50 levels, 100K+ files each). Full version history, granular sharing with VIEW/EDIT/DELETE permissions, and PDF annotation with permanent redaction.

AI-Powered Search

Ask questions in natural language across all your documents. Hybrid search combines semantic vectors with BM25 keywords. Every answer cites the exact source document and page.

PII, NHI & Secret Detection

Auto-scan every document for sensitive data before it enters the AI pipeline. Detect SSNs, emails, medical records, API keys, and credentials. Auto-redact or flag for review.

OCR & Document Intelligence

Extract searchable text from scanned PDFs, images, and mixed-content documents. 100+ languages, RTL support, layout-aware parsing for multi-column and table-heavy files.

Full Audit Trail

Every query, retrieval, LLM prompt, and response is logged. Export deterministic audit traces showing exactly which document chunk produced each sentence.

Permission-Safe Retrieval

DMS permissions are the single source of truth. When you share or revoke access, the AI search index updates instantly. Users only see documents they're authorized to access — impossible to bypass.

Connect External Sources

Already have documents elsewhere? Connect to SharePoint, Alfresco, S3, email, file servers, and REST APIs. Index in-place — no file duplication, no data migration.

Model-Agnostic LLM Gateway

Use any LLM — OpenAI, Azure, Anthropic, local Ollama models. Configure per-knowledge-base with automatic fallback across priority tiers.

Deploy Anywhere

On-premise, air-gapped, your own cloud (BYOC), or managed single-tenant SaaS. Docker Compose or Kubernetes. AES-256 encryption. Keycloak SSO.

// INTERACTIVE_DEMO

See the Full Platform in Action

Click through each screen to explore CordonData's complete document intelligence pipeline — from upload to AI-powered answers.

Ask AI — Grounded answers with citations
CordonData v2.1 • enterprise + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity ↑ Click any item to preview Recent Chats Project Phoenix launch plan Q3 revenue comparison HR policy review Contract clause search Clear all AM Alex Morgan alex.morgan@company.com Platform Knowledge Engine Workspace Workspace: Q3-Strategy ▼ Ask AI In Project_Phoenix_Launch_Brief.pdf, what is theproject codename? Also flag any PII/secret findings. ▸ Reasoning trace (4 steps) 🔍 Searching Q3-Strategy142 docs scanned in 0.18s 📄 Top match: Project_Phoenix_Launch_Brief.pdf • p.2 §Overview • reranked by relevance (98%) 🛡️ Compliance check: CLEAN — no PII/NHI/secrets triggered. Safe to surface verbatim. 💬 Answer The project codename is PHOENIX-7 . Launch targets: APAC, EMEA, NA in Q4 2026. Lead: Sarah Chen. Budget: $2.4M. Codename maps to 3 regional variants. Found in 2 of 3 primary docs and referenced in 14 other downstream artifacts. ⚠ Auto-redacted 0 sensitive tokens. Original raw excerpt available to authorized users only. SOURCES (3) — click chip to jump to highlight 1Project_Phoenix_Launch_Brief.pdf 2APAC_Launch_Strategy.pdf 3EMEA_Launch_Plan.docx 📄 Project_Phoenix_Launch_Brief.pdf — p.2 §Overview This document outlines the launch plan for Project Phoenix. The project codename is PHOENIX-7 . Launching Q4 2026 across APAC, EMEA, and North America. Lead: Sarah Chen. Budget: $2.4M. Contact: sarah.chen@crestsolution.com 📌 Sticky note (Alex) Confirm APAC lead with Maya before sharing. █ █ █ █ █ █ █ █ — PII auto-redacted (SSN) before share DOCUMENT ACTIONS — click any 📋 Copy citation⌘C 🔗 Share link (redacted)⌘S 📥 Open in My Library 🕘 Version history (3) 📝 Add sticky note 🛡️ Re-scan for PII 📤 Export PDF + citations FOLLOW-UPS — click to ask 📅 Launch timeline? 💰 Budget breakdown 🛡 Show all PII in this doc Ask anything — cite, redact, draft, compare... 📎 🔍 🌐 Q3-KB ▼ 🧠 GPT-4o ▼ 🧪 Think Send ↑ 📄 APAC_Launch_Strategy.pdf — p.4 §Regional Breakdown APAC launch budget: $840K (35% of total). Lead: Maya Chen. Timeline: Jan–Mar 2027. Key markets: Singapore, Tokyo, Sydney, Mumbai. Codename referenced as PHOENIX-7 throughout. ⚠ Contains budget figures — compliance scan: CLEAN 📌 Sticky (Maya): "Confirm Singapore regulatory before Jan." Last edited: 3d ago • Visible to: APAC team 🔗 Shared with: maya.chen@, apac-leads@ — expires 30 Jun 📄 EMEA_Launch_Plan.docx — p.7 §Budget & Timeline EMEA budget: €720K. Lead: Lars Vogel (Berlin). Codename PHOENIX-7 maps to 3 regional sub-brands. GDPR compliance review: passed. Data residency: EU-only. ⚠ PII found: lars.vogel@crestsolution.de — auto-redacted in share 🛡 Redaction applied (1 finding) Email: ████████████████████ — PII (personal email) Redacted by: Alex Morgan • 2h ago • Audit vault: #R-4821 Original preserved. Served copy is clean. PHOENIX-7 launch timeline: Q1 2027 — APAC soft launch (Singapore, Tokyo) Q2 2027 — EMEA rollout (Berlin, London, Paris) Q3 2027 — NA full launch (NYC, SF, Chicago) 📄 2 sources • ⚡ 0.12s • 🛡 0 PII triggered PHOENIX-7 total budget: $2.4M APAC — $840K (35%) • Lead: Maya Chen EMEA — €720K (~$780K) • Lead: Lars Vogel NA — $780K (32%) • Lead: Sarah Chen 📄 3 sources • ⚡ 0.15s • 🛡 0 PII triggered ⚠ PII scan results for PHOENIX-7 documents: 1 email found — lars.vogel@crestsolution.de (EMEA_Launch_Plan.docx, p.7) 1 SSN found — ███-██-████ (Project_Phoenix_Launch_Brief.pdf, p.2) 0 NHI0 secrets • Both auto-redacted in shares 📄 3 docs scanned • 🛡 2 findings • Audit vault: #R-4821, #R-4822 🔗 Share "Project_Phoenix_Launch_Brief.pdf" ✕ Close 👥 Recipients alex.morgan@company.com, maya.chen@company.com 🔒 Permission Read-only ✓ Comment ⏱ Expiry 7 days ✓ 24h 30d 🛡 Redaction ⚠ 1 PII finding auto-redacted: SSN ███-██-████ (p.2) Recipient sees redacted version. Original preserved in audit vault. 🔗 Generated link cordon.io/s/8f3c41e2-a9b7-4d2c-8e1f-3a6b9c0d1e2f 👁 47 views • ⏰ Expires 19 Jun 2026 • 💧 Watermarked 📋 Copy link ✕ Cancel 🕘 Version History — Project_Phoenix_Launch_Brief.pdf ✕ Close v3 (current) Alex Morgan • 2 hours ago • +1.2 KB • "Added APAC budget figures" Active v2 Maya Chen • 3 days ago • +0.8 KB • "Updated EMEA regulatory notes" Restore v1 Alex Morgan • 8 days ago • 2.4 KB • "Initial upload from My Library" Restore 📊 Diff view: side-by-side with red/green highlights. Rollback is instant — all citations re-link. Auditors can prove exactly what was said when. Full chain of custody. 📝 Add Sticky Note — p.2 §Overview ✕ Close Note text Confirm APAC lead with Maya before sharing. Type your note here... (supports @mentions) 🎨 Color 👥 Visibility Private ✓ Team Role 📌 Pin note ✕ Cancel 🛡 Re-scan for PII / NHI / Secrets ✕ Close Scanning: Project_Phoenix_Launch_Brief.pdf (12 pages, 1.2 MB) ✅ Scan complete • 2 findings • 0.4s ⚠ PII — SSN (Social Security Number) p.2 §Overview • "███-██-████" • Severity: HIGH Redact ⚕ NHI — Email (potential PHI) p.2 §Overview • "sarah.chen@crestsolution.com" • Severity: MEDIUM Redact ☑ Whitelist Mark as false positive (logged with reviewer identity) 🔴 Redact all ✕ Cancel Original is never modified — only the served copy is redacted. Audit vault: #R-4821
CordonData v2.1 • enterprise + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity ↑ Click any item to preview + New 📁 My Library 👥 Shared with me 🔗 Shared with others ⭐ Starred 🗑️ Trash 🗑️ All User Trash 🌐 Public Shares STORAGE 8.4 GB of 50 GB used 17% used 📁 My Library All folders Browse, search, and sort files and folders in your current library location. 🔍 Search library… Name Description Owner Modified Created Size 📁 Phoenix-Launch-2027 - - 2h ago 2h ago 3.8 MB 📁 Compliance-Audit-Q2 - - 5h ago 5h ago 1.2 MB 📁 Sales-Playbooks - - 1d ago 1d ago 4.5 MB 📁 Engineering-Specs - - 2d ago 2d ago 8.1 MB 📁 HR-Onboarding - - 3d ago 3d ago 920 KB 📁 Legal-Contracts - - 4d ago 4d ago 12 MB 📁 Finance-Reports - - 1w ago 1w ago 2.3 MB 📁 Marketing-Assets - - 1w ago 1w ago 156 MB 📁 Customer-Feedback - - 2w ago 2w ago 450 KB 📁 Public-Share-Links - - 3w ago 3w ago 78 KB Showing 1 to 10 of 10 entries 10 / page ▼ ‹ Previous 1 Page 1 of 1 ⬆ Upload files 📁 New folder 🔗 New share ··· ACTIONS ⬇ Download 👁 Preview 🕘 Manage versions ⇄ Select for Compare ⭐ Add to favorites ℹ️ Properties 💬 Comments 📜 Audit Log 💬 Ask AI 👥 Manage access ➡️ Move to... 📋 Copy to... ✏️ Rename 🔗 Share link 🗑️ Move to trash 🕘 Manage Versions ✕ Close UPLOAD NEW VERSION ✎ Edit Properties 📤 Click to choose file VERSION COMMENT What changed in this version? ⬆ Upload Version HISTORY ✓ Current v1.0 Today, 1:40 AM 1e4b1cc8-6ca2-4434-a27d-44b69483077a.pdf 📄 3.8 MB • application/pdf v0.9 Yesterday, 5:22 PM 1e4b1cc8-6ca2-4434-a27d-44b69483077a.pdf 👥 MANAGE ACCESS Sharing: 1e4b1cc8-6ca2-4434-a27d-44b69483077a.pdf 🔍 adi.prakosa (adi.prakosa@cordom Edit ▼ Invite PEOPLE WITH ACCESS No permissions set — only the owner has access. Done 📋 SELECTION INFO PDF 1e4b1cc8-6ca2-4434-... DOCUMENT 🔗 🕘 🗑 ✓ Details ▼ PROPERTIES NAME 1e4b1cc8-6ca2-4434-a27d-44b69483077a.pdf CREATOR - DESCRIPTION Show More Properties ▼ 📄 DOCUMENT TYPE — Generic / no type — Open Details View → Save PROCESSING ↻ Refresh OCR OCR Ready AI Index AI Ready 💬 Comments 📅 Version History 📜 Audit Log 💬 Ask AI 📄 d9dd3ae1-5c4e-4e3f-b5e9-43692... DOCUMENT ✏ Close Annotator ⬇ Download ↖ Select ✎ Highlight ⛔ Redact A Text 📌 Sticky note ⛔ Stamp Redact recipients (1) @ saikat.kumar@crestsolution.com 🗑 Delete Cancel 💾 Save overlay 1 CONDENSED CONSOLIDATED STATEMENTS OF OPERATIONS (Unaudited) (In millions, except number of shares, which are reflected in thousands, and per-share amounts) Three Months Ended Twelve Months Ended September 28, 2024 September 30, 2023 September 28, 2024 September 30, 2023 Net sales: Products $ 69,958 $ 67,184 $ 294,866 Services 24,972 22,314 96,169 85,200 Total net sales (1) 94,930 89,498 391,035 383,285 Cost of sales: Products 44,566 42,586 185,233 189,282 Services 6,485 6,485 25,119 24,855 Total cost of sales 51,051 49,071 210,352 214,137 Gross margin 43,879 40,427 180,683 169,148 Operating expenses: Research and development 7,765 7,307 31,370 29,915 Selling, general and administrative 6,523 6,151 26,097 24,932 Total operating expenses 14,288 13,458 57,467 54,847 Operating income 29,591 26,969 123,216 114,301 Other income/(expense), net 19 29 269 (565) 📌 Review Q4 Confirm APAC numbers before publication Action
CordonData v2.1 • enterprise + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity ↑ Click any item to preview Platform › Knowledge Engine System Explorer Workspace: Q3-Strategy ▼ 🌐 Unified across: 5 systems ▼ ⌘K to jump 🔍 Search across all... Workspace ▼ + Add system Folder Tree 📂 Q3-Strategy 📁 Phoenix 📄 Project_Phoenix_Launch_Brief.pdf 📄 Phoenix_Budget_2026.xlsx 📁 Policies 📄 HR_Manual.pdf 📄 Security.pdf 📁 Compliance 📄 GDPR.pdf 📁 Reports 📁 Templates 📁 Archive 📁 Shared — Select a folder to browse files — 47 folders • 1,280 docs Total: 8.4 GB indexed ✓ All docs AI-ready 📡 Connected Systems 📁 Knowledge Base 📊 Activity Enterprise DMS #1 DMS Connector • 12,450 docs • 2m ago OK Team Workspace DMS DMS Connector • 8,210 docs • 15m ago OK Legacy File Server File Server • Syncing 3,421/8,900 ··· Cloud Object Storage Cloud Connector • 45,200 docs • 1h ago OK Local Upload Direct Upload • 1,280 docs • Active OK Total: 5 active sources  •  75,560 docs Status: 4/5 healthy, 1 syncing Throughput: 412 docs/min  •  Latency: 187ms avg + Add Connected Source ⚙ Configure Connectors ▾ Enterprise DMS #1 — selected 📊 Total indexed: 12,450  •  Last full crawl: 2 min ago  •  Crawl frequency: Every 5 min 🔗 Endpoint: https://dms.acme.local/cmis/v1.1  •  Auth: OAuth2 + mTLS 📂 Folders scanned: 127  •  ACL preserved: ✓ Yes  •  Webhook: ● Active  •  Errors: 0 ⏱️ Avg latency: 187ms  •  Queue: 0 pending  •  Next crawl: 3 min  •  Owner: admin@company.com ▾ Team Workspace DMS — selected 📊 Total indexed: 8,210 • Last full crawl: 15 min ago • Crawl frequency: Every 15 min 🔗 Endpoint: https://team-dms.acme.local/cmis/v1.1 • Auth: OAuth2 📂 Folders scanned: 89 • ACL preserved: ✓ Yes • Webhook: ● Active • Errors: 0 ⏱ Avg latency: 210ms • Queue: 0 pending • Next crawl: 12 min • Owner: team-leads@company.com ▾ Legacy File Server — syncing 📊 Total indexed: 3,421 / 8,900 • Progress: 38% • ETA: ~12 min 🔗 Endpoint: smb://fileserver.acme.local/docs • Auth: Kerberos 📂 Folders scanned: 42 / 156 • ACL preserved: ✓ Yes • Webhook: ⏳ Pending • Errors: 2 ⏱ Avg latency: 450ms • Queue: 5,479 pending • Next crawl: after sync • Owner: it-admin@company.com ▾ Cloud Object Storage — selected 📊 Total indexed: 45,200 • Last full crawl: 1 hour ago • Crawl frequency: Every 1h 🔗 Endpoint: s3://company-docs-prod • Auth: IAM Role 📂 Buckets: 3 • ACL preserved: ✓ Yes • Webhook: ● Active • Errors: 0 ⏱ Avg latency: 95ms • Queue: 0 pending • Next crawl: 54 min • Owner: cloud-ops@company.com ▾ Local Upload — selected 📊 Total indexed: 1,280 • Last upload: 2 min ago • Status: Active 🔗 Source: Direct upload via web UI / API • Auth: User session 📂 Folders: 47 • ACL: ✓ Per-user • Webhook: ● Active • Errors: 0 ⏱ Avg latency: 45ms • Queue: 0 pending • Owner: alex.morgan@company.com ➕ Add Connected Source ✕ Close 8 built-in connectors + custom microservice 📁 CMISAlfresco, Documentum, FileNet 🌐 REST APIAny JSON API with field mapping 📧 EmailIMAP / Office 365 📂 FilesystemLocal or network share 🗄️ SMB / CIFSWindows shares, NAS ☁️ S3 / ObjectAWS S3, MinIO, Azure Blob 📤 Local UploadDirect web UI / API upload 🔌 CustomWrite a microservice in any language Each connector auto-registers on startup. Sends heartbeats, exposes crawl/test/status API. Add new connectors without modifying the core — just deploy and register. Click a connector type to configure. Custom connectors implement the standard CordonData connector API. 🔄 Force Sync — Legacy File Server ✕ Close Syncing: smb://fileserver.acme.local/docs ⏳ Syncing... 3,421 / 8,900 docs (38%) • ETA: ~12 min 📂 Folders scanned: 42 / 156 • Current: /docs/finance/Q4-reports/ 📄 Last indexed: Budget_Summary_2025.xlsx (2.1 MB, 18 sheets) ⚠ 2 errors (permission denied on /docs/hr/confidential/) — skipped, logged SYNC STATS 📊 Throughput: 412 docs/min • ⏱ Avg latency: 450ms • 🔄 Retries: 3 🛡 ACL sync: enabled • 📝 Change detection: hash-based ⏸ Pause sync ✕ Cancel 📁 Phoenix — 5 files ⋮ Menu 📄 Project_Phoenix_Launch_Brief.pdf1.2 MB 12 pages • 2h ago • ● AI Ready • OCR 97% 📊 Phoenix_Budget_2026.xlsx480 KB 18 pages • 5h ago • ● AI Ready • N/A 📄 APAC_Launch_Strategy.pdf2.1 MB 24 pages • 1d ago • ● AI Ready • OCR 95% 📄 EMEA_Launch_Plan.docx1.8 MB 18 pages • 3d ago • ● AI Ready • N/A 🖼️ Phoenix_Marketing_Plan.pdf3.2 MB 32 pages • 2d ago • ● AI Ready • OCR 89% 📂 Browse all 5 files in Phoenix Right-click any file for actions ACL: Private (folder inherits) • 🛡 AI-safe 📁 Policies — 2 files ⋮ Menu 📄 HR_Manual.pdf1.5 MB 48 pages • 2w ago • ● AI Ready • OCR 98% 📄 Security.pdf920 KB 22 pages • 3w ago • ● AI Ready • OCR 96% Right-click any file for actions ACL: HR-only (private group) • 🛡 0 PII findings 📁 Compliance — 1 file ⋮ Menu 📄 GDPR.pdf1.1 MB 32 pages • 1mo ago • ● AI Ready • OCR 94% Right-click any file for actions ACL: Compliance team • 🛡 0 PII findings 📁 Reports — 1 file ⋮ Menu 📄 Audit_2025.pdf4.1 MB 86 pages • 3mo ago • ● AI Ready • OCR 92% Right-click any file for actions ACL: Auditors + admins • 🛡 2 PII (auto-redacted) 📁 Templates — 2 files ⋮ Menu 📄 NDA_Template.docx120 KB 4 pages • 5mo ago • ● AI Ready • N/A 📄 Contract_Template.docx180 KB 6 pages • 5mo ago • ● AI Ready • N/A Right-click any file for actions ACL: Public (workspace) • 🛡 Templates — no PII 📁 Archive — 1 file ⋮ Menu 📄 Old_Project_Brief.pdf800 KB 18 pages • 8mo ago • ● AI Ready • OCR 91% Right-click any file for actions ACL: Public • 🛡 Read-only (retention policy) 📁 Shared — 1 file ⋮ Menu 📄 Team_Roadmap.docx320 KB 8 pages • 4d ago • ● AI Ready • N/A Right-click any file for actions ACL: Shared with team • 🛡 0 PII 📂 FILE ACTIONS 🔄 Force re-crawl 🧪 Test connection 🔒 View ACL sync status 📋 View sync logs ⚙️ Configure connector 🔁 Restart connector ⏸ Disable connector 📁 FOLDER ACTIONS 🔄 Re-scan all files ⚙️ Folder settings 🔒 Edit ACL ✓ Close 📁 FOLDER ACTIONS 🔄 Re-scan all files ⚙️ Folder settings 🔒 Edit ACL ✓ Close 📁 FOLDER ACTIONS 🔄 Re-scan all files ⚙️ Folder settings 🔒 Edit ACL ✓ Close 📁 FOLDER ACTIONS 🔄 Re-scan all files ⚙️ Folder settings 🔒 Edit ACL ✓ Close 📁 FOLDER ACTIONS 🔄 Re-scan all files ⚙️ Folder settings 🔒 Edit ACL ✓ Close 📁 FOLDER ACTIONS 🔄 Re-scan all files ⚙️ Folder settings 🔒 Edit ACL ✓ Close 📁 FOLDER ACTIONS 🔄 Re-scan all files ⚙️ Folder settings 🔒 Edit ACL ✓ Close Action ✕ Close Action completed successfully ✅ JOB DETAILS 📊 Job ID: #J-4827 • Status: ✓ Completed • Duration: 2.3s ⏱ Started: 2 min ago • Owner: alex.morgan@company.com 📂 Scope: 1 connector • 1,280 docs scanned RESULTS ✅ Indexing completed for 1,280 documents ✅ All ACL permissions preserved ✅ No compliance violations found 📊 Audit log: #AL-4928 — logged with reviewer identity Click Close to return to System Explorer ✓ Done View full report Action
CordonData v2.1 • enterprise + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity ↑ Click any item to preview Platform › Governance & Quality PII & Secret Scanning All Findings (36) PII (12) NHI (3) Secret (1) 🔴 Redact All Reset Document Findings Scan Time Source Action 📄 Employee_Records_Q3.pdf PII-12 NHI-3 SEC-1 1.2s My Uploads 👁 View 📄 Project_Phoenix_Launch_Brief.pdf CLEAN 0.8s My Uploads 👁 View 📄 Vendor_Contract_Draft.docx PII-5 0.9s DMS 👁 View 📄 Compliance_Handbook_2026.pdf CLEAN 1.0s DMS 👁 View 📄 Employee_Onboarding_Form.pdf PII-8 SEC-2 1.4s Cloud 👁 View 📄 Employee_Records_Q3.pdf — Redacted Preview (Safe to Share) Employee: [REDACTED — SSN] | ID: [REDACTED — PII] | DOB: [REDACTED — PII] Email: [REDACTED — Email] | Phone: [REDACTED — Phone] | Address: [REDACTED — PII] Performance review summary for Q3 2025. Employee exceeded targets in all categories with consistent top-quartile ratings across leadership, innovation, and execution. Medical: [REDACTED — NHI/MRN] — cleared for full duty. API key: [REDACTED — Secret] rotated on schedule. Manager: Sarah Chen 🔬 DETECTION RULES ACTIVE SSN Regex (US) Email+Phone NHI/MRN (deberta) Entropy ≥ 4.5 IBAN+SWIFT Credit Card +12 ⚡ LIVE FINDING STREAM 🔴 PII (SSN) @ p.2 of HR_Records.xlsx — 1.2s ago 🟡 NHI/MRN @ p.5 of Patient_Intake.pdf — 4.0s ago 📈 7-day trend PII: ● ● ● ●● ● ●●● 12 today SEC: ● ●● ● ● 3 today 📄 Employee_Records_Q3.pdf — 16 findings ✕ Close 12 PII • 3 NHI • 1 Secret • Source: My Uploads • Scanned 1.2s ago PII FINDINGS (12) ⚠ SSN — "███-██-████" — p.1 §Employee Info — HIGH Redact ⚠ Email — "john.doe@company.com" — p.1 §Contact — MEDIUM Redact ⚠ Phone — "+1-555-0123" — p.1 §Contact — MEDIUM Redact NHI FINDINGS (3) ⚕ MRN — "MRN-48291" — p.3 §Medical — HIGH Redact SECRET FINDINGS (1) 🔑 API Key — "sk-abc123..." — p.5 §Integration — CRITICAL Redact 🔴 Redact all 16 ✕ Cancel Original preserved in audit vault. Redacted copy served to viewers. 📄 Vendor_Contract_Draft.docx — 5 findings ✕ Close 5 PII • Source: DMS • Scanned 0.9s ago ⚠ SSN — "███-██-████" — p.2 §Vendor Info — HIGH Redact ⚠ Email — "vendor@acme-corp.com" — p.2 §Contact — MEDIUM Redact ⚠ Phone — "+1-555-0199" — p.3 §Terms — LOW Redact 🔴 Redact all 5 ✕ Cancel 📄 Employee_Onboarding_Form.pdf — 10 findings ✕ Close 8 PII • 2 Secrets • Source: Cloud • Scanned 1.4s ago ⚠ SSN — "███-██-████" — p.1 §Personal — HIGH Redact 🔑 Password — "TempPass123!" — p.4 §IT Setup — CRITICAL Redact 🔴 Redact all 10 ✕ Cancel 🔴 Bulk Redact — 36 findings across 5 documents ✕ Close ⚠ This will redact ALL 36 findings. Originals preserved in audit vault. 🔴 Processing... 36/36 findings redacted • 0.8s 📄 Employee_Records_Q3.pdf — 16 redacted ✓ 📄 Vendor_Contract_Draft.docx — 5 redacted ✓ 📄 Employee_Onboarding_Form.pdf — 10 redacted ✓ 📄 Project_Phoenix_Launch_Brief.pdf — 0 (CLEAN) ✓ 📄 Compliance_Handbook_2026.pdf — 0 (CLEAN) ✓ ✅ All redactions applied. Audit vault: #R-4830 through #R-4865 📊 Export SOX/HIPAA-ready report with full audit trail 📊 Export report ✕ Done
CordonData v2.1 • enterprise + New chat Tools 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity ↑ Click any item to preview Platform › Knowledge Engine Activity Workspace: Q3-Strategy ▼ Activity Audit All Users My Activity 📥 Export CSV 🔍 Search users by name or email... 📅 30d ▼ ⚙ Filter AM Alex Morgan alex.morgan@company.com Last seen: 1m ago 170logins 41chats 0search 9docs 23RAG 3apps View → A Auditor User auditor.user Last seen: 11m ago 43logins 2chats 0search 0docs 2RAG 1apps View → J Maya Chen maya.c Last seen: 22m ago 1logins 1chats 0search 0docs 0RAG 0apps View → A David Park david.park Last seen: 22m ago 36logins 14chats 0search 0docs 6RAG 1apps View → 📊 SUMMARY — All Users (Last 30 days) 👥 Users: 47 active  •  🔑 Logins: 1,247  •  💬 Chats: 328  •  🤖 RAG: 412  •  📄 Docs: 89  •  🔌 Apps: 23 ⏱️ Avg session: 14m 22s  •  🔍 Top query: "project codename"  •  📂 Most active KB: Q3-Strategy ⚡ Token usage: 2.4M tokens  •  💰 Cost: $187.42  •  🛡️ Scans run: 36 (12 findings)  •  🔗 Shares created: 14 📈 ACTIVITY TIMELINE (last 7 days) MonTueWedThuFriSatSun ● Logins ● Chats Top user: Alex Morgan (170 logins / 41 chats) Busiest day: Friday AM Alex Morgan — Full Activity ✕ Close alex.morgan@company.com • Last 30 days LOGIN HISTORY 🔑 170 logins • Avg session: 22m • IPs: 192.168.1.x, 10.0.0.x • Device: MacBook Pro 📍 Locations: San Francisco (80%), New York (15%), Remote (5%) CHAT ACTIVITY (41 queries) 💬 Top query: "What is the project codename?" (asked 8 times) 💬 Recent: "PHOENIX-7 budget breakdown" • "APAC launch timeline" • "PII scan results" 🧠 Models used: GPT-4o (32), Claude 3.5 (7), Ollama local (2) DOCUMENT ACTIVITY (9 docs) 📄 Viewed: Project_Phoenix_Launch_Brief.pdf (24 views) • APAC_Launch_Strategy.pdf (12) 📤 Uploaded: 3 files • 🔗 Shared: 2 links • 🛡 Scanned: 1 doc RAG & APPS 🤖 23 RAG queries • 🔌 3 app integrations used ⚡ Token usage: 847K • 💰 Est. cost: $62.14 📥 Export user log ✕ Close DP David Park — Full Activity ✕ Close david.park@company.com • Last 30 days LOGIN HISTORY 🔑 36 logins • Avg session: 8m • IP: 10.0.1.x • Device: Windows Desktop 📍 Locations: New York (90%), Remote (10%) CHAT ACTIVITY (14 queries) 💬 Top query: "GDPR compliance status" (asked 5 times) 🧠 Models used: GPT-4o (10), Claude 3.5 (4) RAG & APPS 🤖 6 RAG queries • 🔌 1 app integration ⚡ Token usage: 124K • 💰 Est. cost: $9.87 📥 Export user log ✕ Close 📥 Export Activity Log — CSV ✕ Close Exporting: All Users • Last 30 days • 1,247 logins • 328 chats • 412 RAG • 89 docs ✅ Export complete • 2,847 rows • 1.2 MB • activity_log_2026-06-12.csv CSV COLUMNS user_id, user_name, user_email, action_type, target_doc, timestamp, ip_address, device, location, duration, tokens, cost 📊 SOX-ready format • Includes audit trail • Compatible with compliance officer review ⏱ Retention policy: auto-purge after 90 days (legal-hold override available) 📥 Download CSV ✕ Close
CordonData v2.1 • enterprise 🔍 Global Search 💬 Ask AI 📁 My Library 📂 System Explorer 🛡️ Compliance 📊 Activity 📂 Recent • Phoenix launch • Q3 revenue • HR policy • Contracts AM Alex Morgan alex.morgan@company.com Platform › Knowledge Engine Global Search Workspace: Q3-Strategy ▼ 🔍 project codename | 💡 Operators: "phrase" AND OR -exclude field:value site:kb after:2025 Search About 69 matches indexed in 0.18s • Semantic + BM25 hybrid Sort: Relevance ▼ NAME OWNER MODIFIED KB % 📄 Project_Phoenix_Launch_Brief.pdf ...the project codename is PHOENIX-7. Launching Q4 2026... Alex M. 2h ago 👤 My Uploads 98% 📄 APAC_Launch_Strategy.pdf Section 3.2 references the project codename and lists the codename mappings... Maya C. 1d ago 👤 My Uploads 87% 📄 EMEA_Launch_Plan.docx ...the EMEA project codename rollout schedule was finalized... David P. 3d ago 📁 Shared Drive 72% 📊 Phoenix_Budget_2026.xlsx Q4 budget line for project codename PHOENIX-7. Total: $4.2M... Sarah C. 5h ago 👤 My Uploads 94% 🖼️ Phoenix_Marketing_Plan.pdf ...marketing collateral for project codename targeting 3 regions... Maya C. 2d ago 🌐 Confluence 81% Showing 1-5 of 69 • 1 selected ← Prev Next → 📤 Share (1) 📥 Download 💡 AI Summary Across 5 matched documents, the project codename appears in 9 contexts. Primary: PHOENIX-7 • Cross-referenced: APAC_Launch_Strategy, EMEA_Launch_Plan, Phoenix_Budget_2026 💬 Open in Ask AI → 🗂 Filters 📚 KNOWLEDGE BASE Shared Drive (CMIS) 18 Confluence Wiki 8 Legal Archive 31 My Uploads 18 📄 FILE TYPES PDF 50 MP4 2 XLSX 1 DOCX 1 👥 AUTHORS admin 48 Alex Morgan 14 Maya Chen 7 📅 DATE MODIFIED 📆 Custom Today Week Month Year 📋 ACTION DETAILS 👁 View ℹ Meta 🔗 Share 🔒 ACL 📄 Project_Phoenix_Launch_Brief.pdf 1.2 MB • PDF • 2h ago ● AI Ready ● OCR 97% ● Indexed Last action: — Click any row to see actions Right-click a row for context menu ACTIONS 📂 Open in Viewer 💬 Load in Ask AI 🔗 Share link 📥 Download (redacted) 🛡 Re-scan PII/NHI/Secret 🔴 Auto-redact findings ⫶ Compare with another 🕘 Version history ⭐ Star result WHAT THIS DOES 📂 Open in Document Viewer ← Back 📄 Page 1 / 12 Project Phoenix — Launch Brief CONFIDENTIAL — INTERNAL USE ONLY Overview The project codename is PHOENIX-7, a strategic launch for Q4 2026. This document contains the executive summary, target regions, KPIs, and go-to-market timeline for North America, EMEA and APAC regions. Owner: Alex Morgan • Updated: 2h ago Source: Shared Drive (CMIS) • 1.2 MB PAGES 1 2 3 4 📂 Project_Phoenix_Launch_Brief.pdf 💬 Ask AI 🔍 100% 📥 Save 💬 Ask AI — Phoenix_Launch_Brief.pdf loaded with 12 citations What is the project codename and which regions are we launching in? You • just now AI CordonData • grounded in 2 sources The project codename is PHOENIX-7 and the launch covers 3 regions: North America, EMEA, and APAC. The target launch date is Q4 2026. [1] p.1 [2] p.3 Ask a follow-up about this document... 🔗 Share this document Recipient sees a redacted, watermarked, read-only link. Expiry enforced. SHARE LINK (auto-redacted) https://share.cordondata.com/d/8x2k-p7mq Copy PERMISSIONS 🔒 Read-only | ⏱ Expires in 7 days | 💧 Watermark: recipient.email RECIPIENTS (2) MC Maya Chen SC Sarah Cole + Add 📤 Send Link Cancel 📥 Download — auto-redacted copy PII/NHI/Secrets are stripped before download. Audit log records recipient + findings count. FORMAT 📄 PDF 📝 DOCX 📊 XLSX 🗜️ Compressed .zip REDACTIONS APPLIED (live preview) Original: "...contact [email protected] or call [PHONE_REDACTED]..." Redacted: "...contact ▮▮▮▮@▮▮▮.com or call ▮▮▮-▮▮▮-▮▮▮▮..." 90% — Generating redacted PDF 📥 Download .pdf Cancel 🛡 Compliance re-scan queued Engine: PII (deberta) • NHI (regex + NER) • Secrets (regex + entropy). ETA 8s. 98% PII (312 found) 76% NHI (48 found) 52% Secrets (3 found) PII Verify (queued) PII Strip (queued) Reindex (queued) LIVE LOG [12:04:18] PII pass 1 complete — 312 findings [12:04:19] NHI pass 1 complete — 48 findings (2 NPI, 46 email) [12:04:20] Secret scan running — entropy + regex combined 🔴 Auto-redact all View full report 🔴 Auto-redact all sensitive findings 312 PII + 48 NHI + 3 secrets will be redacted. Original is preserved in audit vault. BEFORE From: jane.doe@acme.com SSN: 123-45-6789 Card: 4111-1111-1111-1111 API key: sk_live_4eC39HqLyjWDarjtT1zdp7dc Patient NPI: 1234567890 Phone: +1-555-867-5309 Address: 742 Evergreen Terrace DOB: 1985-03-14 Driver license: D1234567 (CA) AFTER (redacted) From: ▮▮▮▮▮@▮▮▮▮.com SSN: ▮▮▮-▮▮-▮▮▮▮ Card: ▮▮▮▮-▮▮▮▮-▮▮▮▮-▮▮▮▮ API key: ▮▮_▮▮▮▮_▮▮▮▮▮▮▮▮▮▮▮▮▮ Patient NPI: ▮▮▮▮▮▮▮▮▮ Phone: +▮-▮▮▮-▮▮▮-▮▮▮▮ Address: ▮▮▮ ▮▮▮▮▮▮▮▮▮▮ DOB: ▮▮▮▮-▮▮-▮▮ Driver license: ▮▮▮▮▮▮▮ 🔴 Apply redactions (363 items) Cancel ⫶ Compare with another document Pick a target to diff against. PHOENIX-7 references across 4 sibling documents will be shown side-by-side. CANDIDATE TARGETS 📄 APAC_Launch_Strategy.pdf 87% match → 📄 EMEA_Launch_Plan.docx 72% match → 📊 Phoenix_Budget_2026.xlsx 94% match ✓ 🖼️ Phoenix_Marketing_Plan.pdf 81% match → SIDE-BY-SIDE PREVIEW LEFT: Project_Phoenix_Launch_Brief.pdf "The project codename is PHOENIX-7..." RIGHT: Phoenix_Budget_2026.xlsx "Q4 budget for PHOENIX-7 = $4.2M..." 🕘 Version history — 7 revisions Each revision is content-addressed. Roll back instantly — all views + citations re-link automatically. v7 (current) 2h ago • Alex Morgan • +312 words • redacted 3 PII v6 1d ago • Maya Chen • +89 words v5 2d ago • Alex Morgan • −24 words (legal review) v4 3d ago • David Park • +156 words (APAC section) v3 5d ago • Alex Morgan • +512 words (initial draft) 📥 Download v7 ⫶ Diff v7 vs v6 ⫶ Diff v7 vs v5 ⫶ Diff v7 vs v3 ↩ Roll back to v5 📦 Export all versions ⭐ Starred — Phoenix_Launch_Brief.pdf added Saved to your Starred Results. Visible in sidebar → Starred. Email digest opt-in available. YOUR STARRED RESULTS (4) ⭐ Project_Phoenix_Launch_Brief.pdf just now ✓ ⭐ APAC_Launch_Strategy.pdf 2d ago ⭐ EMEA_Launch_Plan.docx 1w ago ⭐ Phoenix_Budget_2026.xlsx 2w ago Done
// AGENT_BUILDER

Agent Builder & Admin Platform

Beyond search — CordonData includes a full agent-builder platform for creating custom AI assistants, configuring model pipelines, and managing enterprise knowledge at scale.

Custom AI Agents

Build purpose-specific AI agents with custom system prompts, tool configurations, and knowledge base assignments. Each agent can use different LLM models and retrieval strategies tailored to specific business functions.

Global Model Settings

Configure LLM, embedding, reranker, condenser, and vision models globally across all knowledge bases. Set priority tiers with automatic fallback — use OpenAI for primary, local Ollama models as backup.

Visual Workflow Editor

Design complex AI pipelines with a drag-and-drop workflow editor. Chain together data ingestion, text extraction, chunking, embedding, retrieval, and response generation nodes — no code required.

Knowledge Base Management

Create and manage multiple knowledge bases, each with independent data sources, chunking strategies, embedding models, and ACL policies. Monitor indexing status, document counts, and sync health from a unified dashboard.

Processing Pipeline Monitor

Real-time visibility into OCR, compliance scanning, chunking, embedding, and RAG indexing pipelines. Track per-document status, retry failed documents, and monitor throughput across all connected sources.

SSO & Identity Management

Integrated Keycloak SSO with support for Active Directory, LDAP, and OIDC/SAML identity providers. Role-based access control across admin console, chat interface, and API endpoints.

// CONNECTORS

Connect to Everything

CordonData connects to your existing infrastructure through native protocol connectors. No data migration, no file duplication — just secure, in-place indexing.

CMIS

Alfresco, Documentum, FileNet, any CMIS-compliant repository

SharePoint

SharePoint Online & On-Premise via REST API with OAuth2

S3 / Object Storage

AWS S3, MinIO, Azure Blob, any S3-compatible storage

REST API

Any REST API with JSONPath-based field mapping & pagination

Email

IMAP/IMAPS, Office 365, Gmail with attachment extraction

Filesystem

Local & network file systems with recursive directory crawling

SMB / CIFS

Windows file shares and NAS devices via SMB protocol

Local Upload

Direct drag-and-drop upload into the built-in DMS

Self-Registering Microservice Architecture

Connectors run as independent microservices that self-register with the admin platform on startup. Each connector sends periodic heartbeats and exposes a standard REST API for crawl, test, and status operations. Add new connectors without modifying the core platform — just deploy and register.

Auto-Registration Heartbeat Monitoring Standard REST API Independent Scaling Vendor-Agnostic

Enterprise-Ready, by Design

Built from the ground up for the security, compliance, and scale requirements of the world's most demanding organizations.

Air-Gapped Ready

Zero external API calls

AES-256 Encryption

At rest & in transit

Docker / Kubernetes

Single-node to multi-AZ

Keycloak SSO

AD, LDAP, OIDC, SAML

On-Premise

Deploy entirely within your data center. Air-gapped operation with no external dependencies. Full control over infrastructure, networking, and data residency.

  • Bare metal or VM deployment
  • Docker Compose or Kubernetes
  • Local LLM inference via Ollama

BYOC (Bring Your Own Cloud)

Deploy inside your own AWS, Azure, or GCP environment. You maintain control of the infrastructure while we provide the software and support.

  • Your VPC, your security groups
  • Your IAM roles and policies
  • Your encryption keys (BYOK)

Managed Single-Tenant

Let us host it for you — in a dedicated, physically isolated environment. No shared databases, no shared indexes, no cross-tenant data leakage.

  • Dedicated infrastructure per customer
  • 99.9% uptime SLA
  • Managed updates & monitoring

Enterprise-Grade Transparency

We built CordonData to solve the two biggest blockers for Enterprise AI adoption: Data Security and Hallucinations.

// RETRIEVAL_AUDIT_TRACE

Verifiable Retrieval Audit Trace

LLM hallucinations are unacceptable in the enterprise. CordonData provides a deterministic audit trace for every generated sentence. Instantly verify the exact document, page number, and extracted text chunk the AI used to formulate its response.

  • Direct links to source files in your DMS
  • Confidence scoring on vector matches
  • Exact text chunk highlighting
AI Response
Generated in 1.2s
Based on the current guidelines, the Q3 bonus pool has been increased by 15% across the APAC division [1].
Audit Trace: Reference [1]
MATCH_SCORE: 0.94
DOC: APAC_Project_Phoenix_Launch_Brief.pdf
PAGE: 12 | CHUNK: #402
"...the executive board has approved a 15% increase to the bonus pool specifically allocated for the APAC division following record sales..."
JS
John Smith Role: HR Director
Query: "Q3 Layoffs"
Found 4 matching documents.
Indexing Source: Enterprise_DMS/HR_Confidential
ED
Emma Doe Role: Engineering Intern
Query: "Q3 Layoffs"
No results found.
Filtered by Index Authorization Rules
// ZERO_TRUST_ACL

Permission-Safe Retrieval Routing

A search engine is only as safe as its weakest access control. While Keycloak handles seamless identity authentication, CordonData’s native authorization engine takes over at the data layer. When a user queries the system, the vector space is dynamically filtered by cross-referencing their username, group, and authority directly against the indexed document metadata.

  • Secure authentication via Keycloak/Active Directory
  • Index-level authorization (User/Group matching)
  • Impossible to bypass via prompt injection
// NATIVE_DMS

Built-in Document Management System

CordonData includes a full-featured, enterprise-grade DMS — not just a file picker. Upload, organize, version, share, annotate, and collaborate on documents with fine-grained access control, all within your secure infrastructure.

File Upload & Organization

Upload files up to 500MB each via drag-and-drop or folder upload. Organize with unlimited nested folders (up to 50 levels deep, 100K+ files per folder). All files encrypted at rest with AES-256-GCM in MinIO object storage.

Version Control

Upload new versions of any file while preserving full history. View, download, promote, or archive previous versions. Each version is independently tracked with upload timestamps and version labels.

Granular Sharing & Permissions

Share files and folders with specific users at VIEW, EDIT, or DELETE permission levels. Folder sharing cascades to all children. Revoke access instantly — removed users immediately lose search visibility and content access.

Comments & Collaboration

Leave comments on any file or folder. Threaded discussions keep context with the document. Comments respect the same permission model — only authorized users can view or modify them.

PDF Annotation & Redaction

Annotate PDFs directly in the browser with highlights, text notes, sticky notes, stamps, and permanent redactions. Annotations are burned into a new version and saved back to the DMS with full version history.

Public Share Links

Generate password-protected public share links for external stakeholders. Set expiration dates, enforce password complexity, and revoke links at any time. Public access is isolated from internal permissions.

Complete Document Lifecycle Management

Create & Upload

Drag-and-drop, folder upload, bulk operations

Move & Copy

Bulk move/copy with async subtree jobs for large folders

Trash & Restore

Soft-delete with restore. Permanent delete with async cleanup

Search & Browse

Full-text search, keyset pagination, breadcrumb navigation

AI-Ready Indexing

Every file uploaded to the DMS is automatically processed through the full AI pipeline: OCR → compliance scanning → chunking → embedding → vector indexing. Documents appear in "My Library" knowledge base and are instantly searchable via the chat interface.

  • Automatic OCR for scanned PDFs and images
  • PII/NHI/secret scanning before indexing
  • Real-time RAG status visibility per document

Permission-Safe by Design

DMS permissions are the single source of truth for AI access control. When a document is shared or revoked, the vector index updates immediately. Users searching via chat only see results from documents they have explicit permission to access.

  • ACL metadata stored alongside vector embeddings
  • Instant permission revocation propagates to search
  • Ask AI never leaks content across permission boundaries
// COMPLIANCE_ENGINE

Automated PII, NHI & Secret Detection

Before any document enters your AI pipeline, CordonData scans, classifies, and redacts sensitive data — ensuring compliance with GDPR, HIPAA, PCI-DSS, and internal data governance policies.

PII Detection

Automatically identify and classify Personally Identifiable Information across all ingested documents — names, addresses, phone numbers, email addresses, social security numbers, passport numbers, driver's license IDs, and more.

SSN Email Phone Passport DL# DOB

NHI Detection

Detect Non-public Health Information and protected health data — medical record numbers, health insurance IDs, patient identifiers, diagnosis codes, and clinical trial data — ensuring HIPAA compliance.

MRN HIPAA ICD-10 HITECH

Secret & Credential Detection

Scan for leaked API keys, access tokens, database connection strings, private keys, AWS/Azure/GCP credentials, and other secrets accidentally embedded in documents before they reach the AI model.

API Key Token ConnStr PEM

How Compliance Scanning Works

1
Ingest

Document enters the pipeline from any connected source

2
Scan & Classify

Regex + ML models detect PII, NHI, and secrets with confidence scoring

3
Redact or Flag

Auto-redact sensitive spans or flag for manual review based on policy

4
Index Safely

Only sanitized content enters the vector index and LLM context window

// DOCUMENT_INTELLIGENCE

Advanced OCR & Document Intelligence

CordonData extracts structured, searchable text from any document format — scanned PDFs, images, handwritten notes, and complex multi-column layouts — using state-of-the-art OCR and document understanding models.

Scanned PDF OCR

Convert image-based PDFs into fully searchable text. Supports multi-page documents, mixed content (text + images), and RTL languages including Arabic and Hebrew.

Image Text Extraction

Extract text from PNG, JPEG, TIFF, and other image formats. Handles low-resolution scans, skewed documents, and complex backgrounds with high accuracy.

Layout-Aware Parsing

Understands multi-column layouts, tables, headers, footnotes, and callout boxes. Preserves reading order and document structure for accurate chunking.

Multilingual OCR

Supports 100+ languages including CJK (Chinese, Japanese, Korean), Arabic, Cyrillic, and Indic scripts. Automatic language detection for mixed-language documents.

Supported Document Formats

PDF (Scanned & Native)
DOCX / DOC
PPTX / PPT
XLSX / XLS
PNG / JPEG / TIFF
HTML / XML
Markdown / Plain Text
EML / MSG (Email)

Built for Regulated Enterprises

CordonData is purpose-built for industries where data security, compliance, and auditability are non-negotiable.

Healthcare & Life Sciences

HIPAA-compliant AI search across clinical notes, research papers, trial data, and patient records. Built-in PHI detection and redaction ensures protected health information never leaks into AI prompts or vector indexes.

Financial Services

PCI-DSS and SOX-compliant document intelligence. Search across trade confirmations, compliance reports, and internal policies with full audit traceability and PII/secret redaction.

Legal & Compliance

Search across case files, contracts, regulatory filings, and e-discovery documents. Every AI-generated answer is backed by a deterministic citation trail to the exact source paragraph.

Government & Defense

Air-gapped, fully on-premise deployment. No external API calls. Classified document handling with role-based access control at the vector index level. FedRAMP-ready architecture.

Manufacturing & Engineering

Search across technical specifications, CAD documentation, SOPs, and maintenance logs. Connect to SharePoint, network file shares, and legacy DMS without migrating data.

Education & Research

AI-powered research across academic papers, grant proposals, and institutional repositories. Respects copyright and access restrictions with document-level permission enforcement.

// ARCHITECTURE

How CordonData Works

A modular, self-hosted platform that connects to your existing infrastructure. Documents stay in place — CordonData indexes and makes them AI-searchable.

DMS DATA SOURCES — Where Your Documents Already Live 📁 Enterprise DMS 📁 Team Workspaces ☁️ Cloud Object Storage 🖥️ File Servers 📧 Email Archives 🔌 Custom REST APIs CONNECTOR LAYER — Protocol-Native, In-Place Extraction DMS Connectors  |  Cloud Storage Connector  |  File Server Connector  |  Email Connector  |  REST API Connector  |  OCR Service PROCESSING PIPELINE — Async via Kafka 🔍 OCR EngineTesseract + Docling 🛡️ PII/NHI ScannerRegex + ML NER 🔐 Secret DetectorEntropy Analysis ✂️ Chunking512-token, 50% overlap 🧮 EmbeddingVector Generation 📊 Metadata SyncACL + Properties INDEX & QUERY LAYER 🔢 Vector IndexOpenSearch 3.7 (k-NN) 📝 Full-Text IndexBM25 + Keyword 🔗 Hybrid RerankerCross-Encoder Fusion 🔒 ACL Metadata StorePermission-Aware AI & SECURITY LAYER 🤖 LLM GatewayModel-Agnostic Router 🔑 Keycloak SSOOIDC / SAML / LDAP 🛡️ ACL EnforcementPer-Document Filtering 📋 Audit LoggerFull Retrieval Trace 📊 AnalyticsUsage + Cost

Self-Hosted

Runs entirely within your infrastructure — bare metal, VMs, or Kubernetes. No data ever leaves your network. 19 containerized services orchestrated via Docker Compose.

Modular & Swappable

Swap any component: embedding model (OpenAI, Ollama, Cohere), LLM (GPT, Claude, Granite, Qwen), vector DB (OpenSearch, pgvector), or OCR engine.

Permission-Safe by Design

ACLs from source systems (SharePoint, Alfresco, file servers) are preserved and enforced at query time. Users only see documents they have permission to access.

Frequently Asked Questions

Everything you need to know about CordonData's enterprise AI platform.

What makes CordonData different from other enterprise AI search tools?

CordonData is the only platform that combines on-premise RAG, document-level permission enforcement, automated PII/NHI/secret redaction, and advanced OCR in a single self-hosted package. Unlike cloud-only solutions, your data never leaves your infrastructure. Unlike simple RAG wrappers, we provide native connectors to your existing DMS, full audit traceability, and zero-trust retrieval routing.

Can CordonData run completely air-gapped?

Yes. CordonData is designed for air-gapped, offline deployments. You can run the entire stack — OCR, embedding, vector search, LLM inference, and SSO — entirely within your secure network with no external API calls. We support local LLM inference via Ollama and other self-hosted model runtimes.

How does document-level security work?

When documents are indexed, their ACL metadata (owner, group, permissions) is stored alongside the vector embeddings. At query time, the user's identity — authenticated via Keycloak or Active Directory — is cross-referenced against this metadata. The vector search space is dynamically filtered so users only see results from documents they have permission to access. This happens at the index level, making it impossible to bypass via prompt injection.

What document formats and languages do you support?

We support PDF (scanned and native), DOCX, PPTX, XLSX, PNG, JPEG, TIFF, HTML, Markdown, plain text, and email formats (EML/MSG). Our OCR engine supports 100+ languages including CJK, Arabic, Cyrillic, and Indic scripts. We also handle RTL (right-to-left) languages with proper text layer alignment.

How does the PII and secret detection work?

Before any document content enters the vector index or LLM context window, it passes through our compliance scanning pipeline. We use a combination of regex patterns, ML-based named entity recognition, and entropy-based secret detection to identify PII (SSN, email, phone, passport, etc.), NHI (medical records, health IDs), and secrets (API keys, tokens, connection strings). Detected spans can be automatically redacted or flagged for manual review based on your policy configuration.

Can I use my own LLM or embedding model?

Absolutely. CordonData is model-agnostic. You can use OpenAI, Azure OpenAI, Anthropic, local models via Ollama, or any OpenAI-compatible API. The embedding model, reranker, and chat model are all configurable per knowledge base. You maintain full control over which models process your data.

How do I get started?

Join our waitlist or apply for the Design Partner Program. Design partners get white-glove onboarding, direct access to our engineering team, and lifetime pricing lock. We're looking for forward-thinking enterprises to help us stress-test the platform before the stable 1.0 release.

Build With Us: The Design Partner Program

We are soon launching a stable 1.0 release. We are looking for 3 forward-thinking enterprises to help us stress-test our advanced document extraction and hybrid search indexing pipelines.

What to Expect (v0.8)

  • Early Access to Core Features: The foundational RAG engine is operational. You'll help us polish the UI and refine edge cases before the public launch.
  • Collaborative Feedback: Your insights are invaluable. We'll work closely with your team to optimize connector reliability and the overall user experience.
  • Safe Sandbox Deployment: To ensure zero risk to production data, we ask that you provide a dedicated test environment or mock dataset for our initial connection.

The Benefits

  • White-Glove Onboarding: Direct installation and identity provider setup by our founding engineering team.
  • Roadmap Influence: Your feature requests get bumped to the front of the dev queue.
  • Lifetime Pricing Lock: Design partners secure an exclusive, heavily discounted licensing rate in perpetuity.