# AI requires unstructured data to unlock its full potential | Blog | Fivetran

DevFeed: [AI requires unstructured data to unlock its full potential | Blog | Fivetran](<https://devfeed.tech/articles/ai-requires-unstructured-data-to-unlock-its-full-potential-blog-fivetran-78386.md>)

Original publisher: [Read original article](<https://www.fivetran.com/blog/ai-requires-unstructured-data-to-unlock-its-full-potential>)

Author: Jamie Cole

Published: 2026-07-22T17:00:57Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [data-platforms](<https://devfeed.tech/topics/data-platforms.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [stream-processing](<https://devfeed.tech/topics/stream-processing.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [azure](<https://devfeed.tech/tags/azure.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [blob-storage](<https://devfeed.tech/tags/blob-storage.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-data-warehouse](<https://devfeed.tech/tags/cloud-data-warehouse.md>), [code](<https://devfeed.tech/tags/code.md>), [context-for-ai-agents](<https://devfeed.tech/tags/context-for-ai-agents.md>), [data](<https://devfeed.tech/tags/data.md>), [data-movement](<https://devfeed.tech/tags/data-movement.md>), [data-pipelines](<https://devfeed.tech/tags/data-pipelines.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [database](<https://devfeed.tech/tags/database.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [development](<https://devfeed.tech/tags/development.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [unstructured-data](<https://devfeed.tech/tags/unstructured-data.md>)

## AI overview

The article argues that AI agents need access to unstructured business context such as support tickets, emails, contracts, and attachments alongside structured data. It describes how Fivetran moves text fields and files into Snowflake, BigQuery, or Databricks, where warehouse features and dbt models can prepare them for retrieval and AI workflows.

## Source excerpt

Fivetran helps you turn unstructured data into rich context in several ways.