# Welcome

K-AI is a **Document Knowledge Platform (DKP)** — a platform that turns a dispersed, ungoverned document estate into a reliable, observable, AI-consumable knowledge asset. This site is the technical reference for engineers integrating, evaluating, or operating K-AI. For commercial positioning and category overview, see [k-ai.ai](https://k-ai.ai).

## Where to start

* **I want to evaluate K-AI** → [The K-AI Platform](/knowledge-ai/the-k-ai-platform/platform.md). Architecture, security, deployment, compliance.
* **I want to integrate K-AI** → [Choose your auth](/knowledge-ai/get-started/choose-your-auth.md), then dive into [Sources & ingestion](/knowledge-ai/sources-and-ingestion/sources-ingestion.md), [K-AI Audit](/knowledge-ai/k-ai-audit/audit.md), or [K-AI MCP](/knowledge-ai/k-ai-mcp/mcp.md).
* **I want to operate K-AI** → [Operate](/knowledge-ai/operate/operate.md). Deployment, monitoring, runbooks.

## Map of the documentation

* [**Get started**](/knowledge-ai/get-started/audit-quickstart.md) — quickstarts and auth chooser.
* [**The K-AI Platform**](/knowledge-ai/the-k-ai-platform/platform.md) — DKP concepts, 5-layer architecture, roles, security, compliance.
* [**Authentication**](/knowledge-ai/authentication/authentication.md) — Instance API keys, OAuth 2.1, cookies.
* [**Sources & ingestion**](/knowledge-ai/sources-and-ingestion/sources-ingestion.md) — connectors and the Instance API for indexation control.
* [**K-AI Audit**](/knowledge-ai/k-ai-audit/audit.md) — conflict-first audit workflow (K-AI Audit web app + Audit API + MCP).
* [**K-AI MCP**](/knowledge-ai/k-ai-mcp/mcp.md) — Model Context Protocol surface for AI agents.
* [**Operate**](/knowledge-ai/operate/operate.md) — deployment, monitoring, scaling, runbooks.
* [**Reference**](/knowledge-ai/reference/reference.md) — OpenAPI specs, glossary, errors, changelog.


---

# Agent Instructions: 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:

```
GET https://k-ai.gitbook.io/knowledge-ai/get-started/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.