Accepting Design Partners

Your Documents,
Finally Intelligent.

The enterprise DMS that actually understands your files. AI-powered search, automated compliance, and precision OCR — all running securely inside your infrastructure. Stable release arriving soon.

See All Features
Ask AI — Grounded answers with citations
Live Demo
< 200ms
Semantic search latency
100%
On-Premise — your data, your control
100+
Languages · OCR & search
0
Vendor lock-in. Ever.

Everything Your Documents Deserve

A complete platform that stores, secures, searches, and understands every file in your organization — from scanned PDFs to CAD drawings.

Document Management

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

AI-Powered Search

Ask questions in plain English across every document you own. Hybrid search blends semantic vectors with BM25 keyword matching. Every answer cites the exact source — down to the page and paragraph.

PII, NHI & Secret Detection

Every document is scanned before it touches AI. Detect SSNs, emails, medical records, API keys, and credentials automatically. Redact or flag for review — your compliance team stays in control.

OCR & Document Intelligence

Turn scanned PDFs and images into searchable, AI-ready text. 100+ languages with RTL support. Layout-aware parsing handles multi-column reports, complex tables, and mixed-content files with ease.

Full Audit Trail

Every query, every retrieval, every AI response — logged and traceable. Export deterministic audit trails showing exactly which document chunk produced each sentence. Your legal team will thank you.

Permission-Safe Retrieval

Your DMS permissions are the single source of truth. Share or revoke access — the AI index updates instantly. Users only see what they're authorized to see. No exceptions, no workarounds, no prompt-injection bypass.

Connect External Sources

Documents live elsewhere? No problem. Connect SharePoint via Microsoft Graph, Alfresco CMIS/REST, S3, IMAP email, SMB shares, GitHub, and generic REST APIs. Index in-place — zero migration, zero duplication.

Model-Agnostic LLM Gateway

Bring your own model or use ours. OpenAI, Azure, Anthropic, DeepSeek, local Ollama — all supported. Purpose-specific roles (generation, thinking, embedding, reranker, vision) with automatic 3-tier failover.

Workflow Automation & AI Agents

Build no-code document workflows that trigger on upload, classification, or compliance events. Chain AI agents, approval gates, webhooks, and connector actions into repeatable, auditable pipelines.

Deploy Anywhere

On-Premise, air-gapped, your own cloud (BYOC), or managed single-tenant SaaS. Docker Compose or Kubernetes. AES-256 encryption at rest and in transit. Keycloak SSO with AD/LDAP/OIDC/SAML.

Platform Overview

Explore Every Capability

One platform. Every document workflow. Dive deep into each area below.

Product Features

AI-powered Ask AI, My Library DMS, Global Search, admin platform, OCR, and the full feature suite.

Explore features

Security & Compliance

Zero-trust retrieval, PII/NHI detection, audit trails, secure external sharing, Keycloak SSO, and on-premise deployment.

See security

Connectors

Native SharePoint Microsoft Graph, Alfresco CMIS/REST, email, SMB, GitHub, S3, and generic REST connectors — all with live ACL sync.

See connectors

Global Search

Cross-knowledge-base, typeahead search across documents, users, and metadata — with facets, ACL filtering, and cited results.

Explore search

Records & Legal Hold

Declare immutable records, apply retention schedules, place legal holds, and run disposition workflows with full audit.

See records

CAD Viewer & Editor

Render, annotate, and edit DXF drawings in the browser. Import DWG safely via isolated conversion and export to PDF or SVG.

See CAD

SharePoint Graph Connector

Index SharePoint libraries in-place through Microsoft Graph, preserving folder structure and keeping ACLs in sync automatically.

See SharePoint integration

Use Cases

Legal, finance, healthcare, and government teams using CordonData for document intelligence at scale.

See use cases

FAQ

Pricing, deployment options, connector support, security certifications, and AI capabilities — answered.

Read FAQ

Ready to start?

Join the waitlist or apply as a Design Partner for white-glove onboarding and lifetime pricing lock.

The CordonData Difference

Security isn't a feature.
It's the foundation.

Most enterprise AI tools bolt intelligence onto existing infrastructure. We designed CordonData so access control, compliance, and auditability are built into every layer — not patched on afterward.

Permission-safe by design

Not bolted on

Most AI tools retrieve content first, then filter by permission — a dangerous afterthought. CordonData enforces your access controls before the AI ever sees a document. A user asking a question can only receive answers from content they're already authorized to view. No exceptions. No workarounds. No prompt-injection bypass.

Enforced at retrieval time, not presentation time

Genuinely on-premise

Not "VPC with our keys"

Your documents, your servers, your encryption keys. CordonData runs entirely within your infrastructure — no telemetry, no external API calls for document processing, no training on your data. Full air-gap deployment is supported for environments where even outbound internet access is prohibited. If it can't leave your network, it can't leak.

Air-gap capable · No data leaves your perimeter

Connect existing systems

No migration required

Don't migrate your content to yet another system. CordonData connects directly to your existing SharePoint, Alfresco, and REST API sources — indexing documents where they already live, preserving your folder structures, and keeping ACLs in sync automatically. Your users keep their workflows. You get AI superpowers.

Zero document migration · Bi-directional ACL sync

Complete audit trail

Every action, immutably logged

Every AI query, document access, administrative action, and compliance scan is logged with user identity, timestamp, retrieved content reference, and outcome. Your legal and compliance teams can answer "who accessed what, when, and what did the AI tell them" — without filing a ticket to IT.

Per-user · Per-document · Exportable to CSV

Enterprise-Ready. Battle-Tested.

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

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

Frequently Asked Questions

Straight answers about CordonData's enterprise AI platform — no marketing fluff.

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.

Shape the Product: The Design Partner Program

We're preparing a stable 1.0 release and looking for forward-thinking enterprises to help us stress-test our advanced document extraction and hybrid search indexing pipelines. Your feedback shapes the roadmap.

What to Expect (v0.9)

  • Early Access to Core Features: The RAG engine, compliance scanner, OCR pipeline, and workflow builder are operational. You'll help us polish the UI and refine edge cases before the public launch.
  • Direct Line to Engineering: Your insights go straight to the team building the product. We'll work closely with you to optimize connector reliability, search quality, and the overall experience.
  • Safe Sandbox Deployment: To ensure zero risk to production data, we ask that you provide a dedicated test environment or representative dataset for initial connection and validation.

The Benefits

  • White-Glove Onboarding: Direct installation and identity provider setup by our founding engineering team — not a support ticket queue.
  • Roadmap Influence: Your feature requests get prioritized. The product evolves around real enterprise needs, not hypothetical use cases.
  • Lifetime Pricing Lock: Design partners secure an exclusive, heavily discounted licensing rate — locked in for the life of your contract.