This page covers HubSpot as a knowledge source — syncing Knowledge Base articles into the AI’s training index. For operating HubSpot (tickets, handoff, conversations, CRM context), see the HubSpot integration.
What you get
- Published articles from your portal’s public search index. Whole-account sync today — no per-knowledge-base or per-category picker.
- Drafts are not synced. Only articles HubSpot has published and indexed for site search are pulled. Draft, scheduled, and unpublished articles stay in HubSpot only.
- Source URLs preserved. Each synced article keeps its public HubSpot help-center URL so the AI can link back to it.
What’s not supported today
- Draft or unpublished articles. HubSpot does not expose draft KB content through any third-party API OpenCX can call today. Publish an article in HubSpot first, or use another source (manual upload, website crawler) for draft content.
- Per-knowledge-base or per-category scoping. The whole portal’s published Knowledge Base index is pulled. Use the Website crawler as a workaround if you only want a publicly reachable subset.
- Full HTML bodies via API. Site search returns indexed snippets (LONG mode). For full-page HTML mirroring, use the Website crawler against your help center domain.
Related Documentation
Connect HubSpot Knowledge Base
Private App access token.
Troubleshooting
Auth errors, missing articles.
HubSpot integration
Tickets, handoff, CRM context.
Connect a knowledge source
All sources.