What challenges did Rocket Close face before AI implementation?

Rocket Close processed approximately 2,000 abstract package files daily, each averaging 75 pages. Manual extraction took about 10 hours per package, creating bottlenecks, high costs, human error, and an inability to keep up with demand spikes.

What was the impact of the AI solution?

Processing time dropped from about 30 minutes of manual effort per package to under 2 minutes end-to-end. The proof of concept achieved about 90% overall accuracy, with large-scale testing across 1,792 samples and over 44,000 data fields showing 89.71% accuracy. The architecture is designed to scale to more than 500,000 documents annually.

Source

Rocket Close automates mortgage abstract package processing with Amazon Textract and Amazon Bedrock

Use case typeIntelligent document processingUpdated Jun 13, 2026

Rocket Close, a Detroit-based title and appraisal management company within the Rocket Companies environment, transformed manual mortgage abstract package processing into an automated workflow using AWS services. The solution uses Amazon Textract for OCR and Amazon Bedrock with Anthropic Claude for document classification, segmentation, and field extraction, with Amazon S3 for storage.

Organization: Rocket Close
Industry: Finance
Location: United States
Published: April 2026

Reported outcomes

90%

accuracyQuality & accuracy

30 minutestime2 minutestime89.7%accuracy

Strategic outcomes

Speed & agilityStreamlined end-to-end document processingScale & capacityBuilt architecture for annual document scale

Catalog median for quality & accuracy deployments: +90% across 282 reported metrics. Compare benchmarks →

Primary read

Use case focus

Showing 3 of 3

1Document Processing Automation
2Intelligent Document Processing
3Workflow Automation

Rocket Close processed approximately 2,000 abstract package files daily, each averaging 75 pages.
Manual extraction took about 10 hours per package, creating bottlenecks, high costs, human error, and an inability to keep up with demand spikes.

A two-stage pipeline first uses Amazon Textract to convert PDFs and images into machine-readable markdown while preserving structure, then uses Amazon Bedrock foundation models with domain-specific prompts and knowledge resources to classify, segment, and extract fields into standardized JSON.
The team used mortgage glossaries, data dictionaries, prompt engineering, and a domain-aware evaluation framework to improve accuracy.

Technologies

Amazon Textract Amazon Bedrock Amazon S3 Anthropic Claude 3

Processing time dropped from about 30 minutes of manual effort per package to under 2 minutes end-to-end.
The proof of concept achieved about 90% overall accuracy, with large-scale testing across 1,792 samples and over 44,000 data fields showing 89.71% accuracy.
The architecture is designed to scale to more than 500,000 documents annually.

Architecture

Two-stage document processing pipeline: Amazon Textract performs OCR and preserves layout hierarchy by converting PDFs/images into machine-readable markdown stored in Amazon S3; Amazon Bedrock foundation models then classify, segment, and extract fields using domain-specific prompts and knowledge resources, outputting standardized JSON.

Implementation partners1

AWS Generative AI Innovation Center

Sources & evidence1

Groundedness: 5/5Type: Blog PostPublished: Apr 2, 2026Publisher: AWSEvidence: VendorConfidence: Medium

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence