> 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/get-started/audit-quickstart.md).

# Quickstart — K-AI Audit

Five minutes to your first resolved conflict. This walkthrough uses the K-AI Audit web app in the browser. For programmatic / AI-agent driven workflow, see the [K-AI Audit MCP](/knowledge-ai/k-ai-mcp/audit-tools.md).

## Prerequisites

* A K-AI account on your organisation's space.
* An audit instance with documents already indexed (Document Stewards typically have this).

## Steps

1. Open `https://app.kai-studio.ai` in your browser.
2. Sign in (local password or Microsoft SSO, depending on your org's configuration). The `kai_auth` cookie is set automatically — see [Authentication — Cookies](/knowledge-ai/authentication/cookies.md).
3. Land on the **Dashboard**. The list shows every audit instance you can access, with counts of open conflicts, pending mandatory questions, and missing subjects.
4. Pick an instance with open conflicts. Click it.
5. Click **Conflicts** in the sidebar. Default filter `state=OPEN`.
6. Click the first conflict. The detail view shows two conflicting excerpts side-by-side, plus links to the source documents.
7. Compose your expert answer in the answer panel. Submit.
8. The platform displays **modification recommendations** for each impacted document — apply them in your source system (SharePoint, Confluence, etc.).
9. Click **Mark managed** to close the conflict.

{% hint style="info" %}
Want to drive this from Claude / Cursor / Le Chat instead? See the [K-AI MCP audit tools](/knowledge-ai/k-ai-mcp/audit-tools.md).
{% endhint %}

## Next steps

Continue with the full audit reference, or run the same flow from an LLM:

* Read the full [K-AI Audit workflow](/knowledge-ai/k-ai-audit/audit.md).
* Try the same flow from an LLM via the [K-AI MCP cookbook](/knowledge-ai/k-ai-mcp/cookbook.md) (Recipe 2 — Resolve an open audit conflict from an LLM).


---

# 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/get-started/audit-quickstart.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.