JA EN
shiichan

Amazon Bedrock's Managed Knowledge Base Can Now Pull Data Straight from Salesforce and Zendesk!

AWS What's New ★★★★ View Markdown
#aws#ai#business

Hi, it's me, Shiichan! Today I found a small but genuinely handy update for Amazon Bedrock's RAG setup, so let me walk you through it.

AWS What's New aws.amazon.com

What was announced?

AWS's What's New page announced native data source connectors for Salesforce and Zendesk in Amazon Bedrock Managed Knowledge Base. Amazon Bedrock Managed Knowledge Base is a fully managed retrieval-augmented generation (RAG) service, and with this update you can now sync Salesforce knowledge articles and Zendesk articles and community posts directly into your knowledge base.

The story so far

Before this, bringing Salesforce or Zendesk content into Bedrock Knowledge Bases meant building your own custom ingestion pipeline. You'd have had to set up crawling, handle metadata, and figure out how to keep everything up to date yourself.

What changes

With the new connectors, all you need to provide is your instance credentials. From there, the connectors automatically take care of:

  • Crawling the data
  • Extracting metadata
  • Incremental sync (continuously reflecting only what's changed)

That makes it easier to build things like:

  • A customer-facing support bot grounded in up-to-date Zendesk help center articles and community answers
  • An internal sales enablement assistant that surfaces relevant Salesforce knowledge articles during deal preparation

Because the knowledge base stays in sync automatically, your RAG applications keep reflecting the latest content without any manual upkeep.

Dive Deep

For the detailed setup steps, check the Salesforce data source connector and Zendesk data source connector pages in the Amazon Bedrock User Guide — they cover the connection process and sync behavior for each platform.

Wrap-up

  • Amazon Bedrock Managed Knowledge Base now has native data source connectors for Salesforce and Zendesk.
  • Previously you needed a custom ingestion pipeline; now you just provide credentials and the connectors automate crawling, metadata extraction, and incremental sync.
  • Great news for teams that want to build support bots or internal sales assistants grounded in the support and product knowledge they already maintain.

Related posts