Do you have a massive amount of documents scanned that you need to extract data from?

Then you may want to check out AWS’s Gen AI Intelligent Document Processing tools.

It’s basically a document processing pipeline in a box. You can quickly spin it up using IaC(Sadly not Terraform, but I could see why they chose CloudFormation).

They have a lot of interesting use cases documented, like classification, how to add a “human in the loop”, fine-tuning, models and a lot more.

And if you have jumped on the Agentic bandwagon, they even have an MCP integration.

I strongly recommend at least using this as a reference for your document parsing pipeline.

If you need help setting up something like this, feel free to reach out and set up a time to chat.