Documentation Index
Fetch the complete documentation index at: https://docs.open.cx/llms.txt
Use this file to discover all available pages before exploring further.
This page covers ingestion — getting your content into the AI’s training index so it can ground answers. If you want the AI to operate a third-party platform (route tickets, send messages, run AI Actions), those capabilities live under Integrations. Vendors that appear in both — Zendesk, Shopify, Intercom, Front — link across from each overview page.
Connect today
Match the source system first — don’t duplicate content just to suit the connector.| If your content lives in… | Use |
|---|---|
| A public help center or website | Website crawler |
| A Zendesk Help Center | Zendesk |
| Intercom segments | Intercom |
| A Front Help Center | Front |
| Confluence spaces | Confluence |
| A Notion workspace | Notion |
| A Shopify store (pages, blog, products) | Shopify |
| GitBook documentation | GitBook |
| Freshdesk Solution articles | Freshdesk |
| You want to author directly inside OpenCX | Help Center |
| You need a specific Q&A or a rule | AI Instructions |
How a source gets connected
Open Data Sources
Sign in to your OpenCX dashboard and go to AI Training → Data Sources.
Pick the source
Click Add source and select the connector. Each source has its own credential fields — the Connect page for each vendor mirrors the dashboard form label-for-label.
Wait for the first sync
The first run pulls everything historical. It takes minutes to hours depending on volume. Progress shows on the source row.
Verify in AI Instructions
Open AI Training → AI Instructions. Synced content appears grouped by source. Check a known article — it should show with the source name and the expected visibility (eye icon).
What to expect after connecting
| Value | |
|---|---|
| Sync cadence | Most sources poll every few hours. The website crawler runs on an interval you set (default 7 days, minimum 24 hours). Trigger a manual sync from the source row anytime. |
| Visibility derivation | Every item is tagged public or internal from the source system’s own signals (drafts, user segments, space type, publish status). Rules per source are on each Connect page. |
| Index scope | One knowledge index per OpenCX org. Separate knowledge pools mean separate orgs — flag it with support if you’re hitting this. |
| Deletion | Removing a source deletes the synced items from the index. The content in the source system is untouched. Re-adding re-pulls everything. |
Related Documentation
AI Instructions
Rules, Q&A pairs, and AI persona edited directly in OpenCX.
Help Center
Author customer-facing articles that also train the AI.
Additional sources
Don’t see your tool? Browse and request it.
Agent Knowledge overview
The three ways OpenCX learns.