> 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/integrations/knowledge-base/confluence.md).

# Confluence

Connect Confluence to Siit so your existing wiki powers AI answers, agent replies, and the Portal Knowledge Base. Pages stay in Confluence, your team keeps editing where they already work

### What you get

* **Live sync from Confluence to Siit.** Selected spaces and pages sync into Siit Articles and refresh automatically — edits made in Confluence flow into Siit on the next sync.
* **Source of truth stays in Confluence.** Siit reads from Confluence. It never modifies your pages.
* **Powers every Siit AI surface.** Synced articles are used by the Triage Agent (answers and deflection at intake) and the IT Agent (autonomous answers in Slack, Teams, and the Portal), with source citations linking back to the original Confluence page.
* **Your page tree, kept as categories.** Siit mirrors the structure of each synced space, so articles land where they sit in Confluence instead of in one flat list.
* **Searchable Portal Knowledge Base.** Employees browse and search synced Confluence content directly in the Siit Portal.
* **Agent-friendly inserts.** Agents can insert synced articles directly into request replies as rich cards.
* **Source tracking.** Every synced article in Siit shows "Source: Confluence" with a link back to the original page.

### How the sync works

* **Initial import** — once you authorize Confluence and pick the spaces or pages you want synced, Siit pulls them in and converts each one into a Siit Article.
* **Continuous sync** — synced content refreshes on a schedule. Confluence edits flow into Siit automatically.
* **Scope-by-space** — you control exactly what's synced. Start with one or two high-value spaces, then expand.
* **Permissions are respected** — Siit honors Confluence's space and page restrictions. Pages the connected user can't access won't appear in Siit.
* **Status preserved** — synced articles can be Draft or Published in Siit. You decide when to make them visible to employees.
* **Categories follow the page tree** — each synced space becomes a category, and the folders and parent pages inside it become categories under it. Every synced page is filed under the category that matches its place in Confluence, and moving a page in Confluence moves its article on the next sync. A page that leaves a synced space is archived in Siit rather than left behind in the wrong place.

{% hint style="info" %}
Browsing shows two levels below the space: the folders and pages directly inside it, then the folders and pages directly inside those. A page nested deeper than that is listed under its second-level category, so employees never have to click through five levels of wiki to reach an article. The space itself only shows as a category when it holds articles of its own.

Categories and articles you created in Siit yourself can sit under a Confluence category, and Siit moves them up to the nearest listed level so they stay reachable.
{% endhint %}

### Where synced Confluence content shows up

* **Portal Knowledge Base** — employees search and browse synced articles in the Siit self-service portal.
* **Triage Agent** — suggests the relevant Confluence-sourced article to an employee at intake, before a request is created.
* **IT Agent** — the AI Agent cites Confluence-sourced articles when answering employees in Slack, Teams, or the Portal.
* **Request replies** — agents insert synced articles directly into responses as rich cards.
* **Workflow actions** — automated replies can attach Confluence-sourced articles (e.g., "send the VPN setup guide when an access request is submitted").

### Before you connect

* A Confluence admin able to authorize the connection.
* An Atlassian account with read access to the spaces you want synced. A dedicated service user is recommended so the integration survives admin turnover.
* A clear idea of which spaces to sync first. Quality beats quantity for AI accuracy — start with your most-used internal docs.

### Connect Confluence

1. In Siit, go to **Settings → Workspace → Integration library**, find **Confluence** in the Knowledge Base section, and click **Connect**.
2. Enter your Confluence site URL (e.g., `yourcompany.atlassian.net`) and authorize with an Atlassian account that has read access to your target spaces.
3. Pick the space(s) you want imported as Articles.
4. Run the initial sync and review the imported Articles in **Context → Articles**.

For the detailed walkthrough, see our Help Center guide: [Confluence integration setup](https://help.siit.io/confluence-integration).

### After the connection

* **Review imported Articles** in **Context → Articles**. Each one shows "Source: Confluence" with a link to the original page.
* **Publish what's ready.** Synced articles default to a state where you can review and publish them deliberately.
* **Check the categories** — Siit rebuilds them from your Confluence tree on every sync, so tidy the tree in Confluence rather than re-filing articles in Siit.
* **Enable AI** — make sure the Triage Agent and the IT Agent are configured to use your Articles. The more high-quality content you sync, the better the AI performs.
* **Validate suggestions** — over the first week, watch which articles AI surfaces in real conversations. Retire or rewrite anything that's outdated or noisy.

### Sync frequency

Confluence content refreshes automatically on a schedule. Trigger an immediate refresh from **Settings → Workspace → Integration library → Confluence → Synchronize** if you've just edited a critical page and need it reflected in Siit straight away.

**Synchronize** hides itself while a sync is running and for 3 hours after the last one, so it reappears once a new run can usefully start.

### Common use cases

* **AI-powered self-service.** Employees ask "How do I request VPN access?" in Slack. The IT Agent searches synced Confluence pages, finds the matching guide, and answers with a source link — no ticket created.
* **Faster agent replies.** An agent opens a new password-reset request and inserts the right Confluence-sourced article into the reply from the composer's article picker.
* **Portal browsing for new hires.** A new hire lands on the Siit Portal and browses synced Confluence onboarding pages — finding answers before their Day-1 questions pile up.
* **Deflection at submission.** When an employee starts submitting a service in the Portal, Siit suggests the relevant Confluence article first; many employees resolve it themselves.
* **Content lifecycle alignment.** Your IT or HR team edits a policy page in Confluence. On the next sync, every Siit surface reflects the update — no manual republishing.

### Tips

* **Start with a focused scope.** Sync the one or two spaces where your highest-quality, most-used documentation lives. Don't sync your entire Confluence site.
* **Title pages as questions employees ask.** "How do I request VPN access?" retrieves better than "VPN Access Procedure."
* **Use a dedicated service account.** Atlassian access is tied to a user — a dedicated service user keeps the integration stable across team changes.
* **Keep one source of truth per topic.** If the same content exists in Confluence and another tool, pick one. AI can't judge which version is canonical.
* **Review what AI is surfacing.** In **Context → Articles**, the analytics view shows which articles AI suggests most often. Low-quality or outdated ones can be retired.

### Help Center guides

* [Confluence integration setup](https://help.siit.io/confluence-integration) — step-by-step setup with screenshots

### Troubleshooting

**Spaces missing from the picker.** The connecting user lacks access to those spaces in Confluence. Either grant the user access or reconnect with a different account.

**A synced article is empty or partial.** Some Confluence macros (especially third-party ones) may not render in Siit. Edit the Confluence page to use native macros where possible, then re-sync.

**Edits in Confluence aren't reflected in Siit.** The sync runs on a schedule. Trigger an immediate refresh from **Settings → Workspace → Integration library → Confluence → Synchronize**.

**AI isn't suggesting Confluence articles.** Confirm the Article is set to **Published** in Siit (Drafts are excluded from AI). Also check that the Triage Agent or the IT Agent has Articles enabled as a source.

**An article moved category on its own.** That is the tree sync doing its job: the page moved in Confluence, so its article followed. Move it back in Confluence rather than in Siit, or the next sync undoes the change.

**"Authorization failed" on connect.** The Atlassian account doesn't have access to the Confluence site, or the site has restricted third-party app installs. Try with a Confluence admin account.

**"Connection lost" or reauthorization needed.** The Atlassian token has been revoked or expired. Reconnect from **Settings → Workspace → Integration library → Confluence**.


---

# 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/integrations/knowledge-base/confluence.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.