> For the complete documentation index, see [llms.txt](https://k-ai.gitbook.io/knowledge-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://k-ai.gitbook.io/knowledge-ai/the-k-ai-platform/platform.md).

# 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

| Page                                                                                  | Summary                                                                |
| ------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- |
| [What is a DKP](/knowledge-ai/the-k-ai-platform/what-is-a-dkp.md)                     | The category K-AI defines and why it matters in 2026.                  |
| [Govern · Clean · Activate](/knowledge-ai/the-k-ai-platform/govern-clean-activate.md) | The three disciplines and the six founding principles.                 |
| [5-layer architecture](/knowledge-ai/the-k-ai-platform/architecture.md)               | Sources → Ingestion → Semantic Document Layer → Governance → Exposure. |
| [Neural Semantic Graph](/knowledge-ai/the-k-ai-platform/neural-semantic-graph.md)     | K-AI's proprietary semantic representation underneath the platform.    |
| [Roles model](/knowledge-ai/the-k-ai-platform/roles.md)                               | Owner, Authority, Steward, Producer, Consumer, Engineer (DocOps).      |
| [Security & isolation](/knowledge-ai/the-k-ai-platform/security.md)                   | Hybrid tenancy, ACL mirroring, encryption, audit trail.                |
| [Deployment models](/knowledge-ai/the-k-ai-platform/deployment.md)                    | SaaS, on-premise Kubernetes, Snowflake Native App.                     |
| [Compliance](/knowledge-ai/the-k-ai-platform/compliance.md)                           | 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](https://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](/knowledge-ai/get-started/choose-your-auth.md) — pick an auth surface and fire a first call.
* [Sources & ingestion](/knowledge-ai/sources-and-ingestion/sources-ingestion.md) — wire up a connector and start the first indexation.
* [Operate](/knowledge-ai/operate/operate.md) — deployment models, monitoring, runbooks for production.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://k-ai.gitbook.io/knowledge-ai/the-k-ai-platform/platform.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.