Overview
K-AI is a Document Knowledge Platform (DKP) — a market category K-AI defines for governing, cleaning, and activating an enterprise's unstructured document estate. This section covers the platform's foundations: what a DKP is, the three disciplines (Govern · Clean · Activate), the five-layer conceptual architecture, the Neural Semantic Graph, the role model, security posture, deployment options, and compliance footprint. It is the umbrella description of the platform as a whole — every other section in this documentation (Authentication, Sources & ingestion, K-AI Audit, K-AI MCP, Operate, Reference) is a slice of what is introduced here.
Sub-pages
The category K-AI defines and why it matters in 2026.
The three disciplines and the six founding principles.
Sources → Ingestion → Semantic Document Layer → Governance → Exposure.
K-AI's proprietary semantic representation underneath the platform.
Owner, Authority, Steward, Producer, Consumer, Engineer (DocOps).
Hybrid tenancy, ACL mirroring, encryption, audit trail.
SaaS, on-premise Kubernetes, Snowflake Native App.
AI Act, GDPR, sectoral regulations.
Why this section exists
This section is written for engineers and architects evaluating K-AI on technical grounds — what the platform is, how it is structured, where it sits relative to adjacent categories (ECM, Data Catalog, AI workplace assistant), and what it commits to. For commercial positioning, case studies, and pricing, the audience goes to k-ai.ai. For build, integrate, and operate details (connectors, APIs, MCP, OAuth, runbooks), the rest of this documentation takes over from here.
Next steps
Choose your auth — pick an auth surface and fire a first call.
Sources & ingestion — wire up a connector and start the first indexation.
Operate — deployment models, monitoring, runbooks for production.
Last updated