automation

IDP Accelerator: Automate Document Processing

Name: IDP Accelerator: Automate Document Processing
Author: aws-solutions-library-samples

Extract info at scale with IDP Accelerator. For founders seeking document automation.

From the repo · “The IDP Accelerator provides a scalable, serverless approach for automated document processing and information extraction using AWS services, such as Amazon Bedrock Data Automation and Amazon Bedrock foundational models. It combines generative AI and optical character recognition (OCR) to process documents at scale.”

317 stars+2★ this week123 forksPythonGuide quality 8/10 · reviewed Jul 9Updated 10/23/2026100% free · open source

What it does

The Accelerated Intelligent Document Processing on AWS tool extracts information at scale from various document types using machine learning, enabling founders to automate document processing tasks.

When to use it

•You need to extract data from a large volume of documents, such as invoices or contracts.
•You want to automate the process of classifying and routing documents based on their content.
•You require a scalable solution for document processing that can be integrated with other AWS services.

Ready-to-paste prompt

python workflow.py --document-type invoice --input-file sample_data/invoice.pdf --output-bucket my-bucket

Heads up: Make sure you have the necessary AWS IAM permissions and credentials set up, as the tool uses AWS services such as S3, Lambda, and Textract, which require proper authentication and authorization.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/accelerated-intelligent-document-processing-on-aws && curl -fsSL https://workflowstacks.com/api/skills/accelerated-intelligent-document-processing-on-aws/claude-skill -o ~/.claude/skills/accelerated-intelligent-document-processing-on-aws/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

226.4M

source size

MIT-0

license

Key files

package.json

pyrightconfig.json

README.md

File tree

.ash/

.claude/

.cline/

.github/

benchmarks/

config_library/

docs/

docs-site/

feature-platform/

iam-roles/

images/

lib/

make/

nested/

notebooks/

patterns/

samples/

scripts/

security/

src/

workshop/

.cfnlintrc.yaml

.clinerules

.dockerignore

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/accelerated-intelligent-document-processing-on-aws && curl -fsSL https://workflowstacks.com/api/skills/accelerated-intelligent-document-processing-on-aws/claude-skill -o ~/.claude/skills/accelerated-intelligent-document-processing-on-aws/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

aws-solutions-library-samples

Language

Python

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Automate replies to your customer reviews

The workflow reads your reviews and drafts a personalized reply for each: warm thanks for happy customers, careful and de-escalating for unhappy ones. Nothing posts automatically — you approve every draft.