> For the complete documentation index, see [llms.txt](https://docs.siit.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.siit.io/data-management/articles.md).

# Articles

Articles are your internal knowledge base. Write them in Siit or sync from Notion, Confluence, or Slab, then use them in the Portal, request replies, workflows, and AI answers

Articles are your internal knowledge base inside of Siit. Create or sync content once and use it everywhere—Portal, request replies, workflows, and AI. Siit centralizes your articles, keeps permissions aligned, and tracks usage so you know what helps.

**Where articles show up**

* Portal → Knowledge base: searchable, categorized content for employees
* Request conversation: insert an article in a reply or workflow. Communication; renders as a rich card
* Triage Agent and IT Agent: answer questions and cite articles as sources; suggest articles in Slack/Teams and the Portal

**Ways to add content**

* Write directly inside of Siit
  * Rich editor (headings, lists, images, links)
  * Draft/Publish, author attribution, categories
* Sync from your external Knowledge Base
  * Notion, Confluence, Slab
  * Choose spaces/pages to sync; updates stay in sync on a schedule
* Save Slack messages to Articles
  * Add the 🧠 reaction to any Slack message (admins)
  * Siit captures the message, thread context, and links it as a draft article
  * You’ll see a success toast in Slack; review and publish in Context → Articles

**Governance and visibility**

* Categories: organize by team or topic (IT, HR, Policies, Security)
* Audience: respect rights and article permissions
* Status: Draft vs. Published; edits create a history and keep links stable
* Source tracking: each article shows its source (Siit, Slack, Notion, Confluence, Slab)

**Analytics**

* View requests resolved with article sends to measure deflection
* Most suggested articles tell you which questions are being asked most frequently.

**Best practices** :bulb:

* Title articles as questions employees ask (“How do I reset my Okta MFA?”)
* Keep steps short with screenshots or GIFs; add last‑updated and owner
* Localize key content or use AI’s language‑aware suggestions
* Review top‑used and low‑rated articles monthly; retire duplicates created from Slack saves
* Enable article suggestions on the Triage Agent so employees receive relevant articles before a request is created


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.siit.io/data-management/articles.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
