HubSpot · Connector
How do we connect HubSpot to AI agents on our own infrastructure?
Katonic connects to HubSpot, reads contacts, deals and blog posts and indexes them in the Knowledge Engine on infrastructure you control. Agents answer from them with a model you serve, so your customer records and the questions are not sent to a public AI service.
What it reads.
From HubSpot.
- 01Contacts
- 02Deals
- 03Blog posts
Through: HubSpot CRM and CMS APIs, v3
Where the content goes
Into a knowledge store you run.Content is pulled into the Knowledge Engine on infrastructure you own or control, and indexed there. Agents answer from it with a model you serve. The documents, the index and the questions are not sent to a public AI service.
How it signs in
The access token of a private app that you create in HubSpot.
The set-up dialog asks for
- Private app token
Permissions
Access is set on the source in Katonic: everyone given access to the source can retrieve its documents. The permissions HubSpot holds for each item are not read.
Sync
Incremental, by last-modified date, and full.
You set how often the source is read again, in minutes, hours, days or weeks.
Which HubSpot records does it read?
Contacts, deals and blog posts. Each of the three can be turned off.
Who can retrieve the records it indexes?
Everyone given access to the source in Katonic. HubSpot's own permissions are not read, so set that access with the records in mind.
Where are the records indexed?
In the Knowledge Engine, on infrastructure you own or control. They are not sent to a public AI service.