How e-Core optimized data extraction for a Real Estate client with AWS

e-Core • June 11, 2025

About the Client


This e-Core client is a technology company focused on the real estate sector. Its web platform provides real-time data, such as insights, market reports, search tools, property appraisals, and investment feasibility analysis for real estate professionals, brokers, and asset managers.


The Challenge


The company was facing challenges in extracting property registry data for one of its property appraisal solutions. These registries are official documents containing essential information about a property and were being manually extracted by engineers, resulting in significant costs for the company. Additionally, with manual extraction, approximately 450 processes were carried out per month, despite high demand.

Manual analysis of property registries is critical to properly evaluating real estate assets. However, with the growing use of properties as collateral for credit, the company faced an unsustainable scenario, needing to process over 1,000 documents per month, more than double its current capacity. Manual extraction also increased operational costs and made it difficult to access information efficiently, limiting the company’s growth potential.

As a result, the company sought an automated and efficient method for extracting data from property registries to improve operational efficiency.



The e-Core Solution


e-Core conducted an in-depth study to design an appropriate architecture that would allow the extraction of relevant information from property registry documents accurately and quickly, aligned with the company’s requirements. The client defined specific criteria, including: key fields to be extracted, total number of pages per registry, and the ability to manually trigger the process.

To meet the requirement for manual initiation, we recommended using AWS Step Functions for orchestration, allowing the registry data extraction process to be started manually or automatically. The extraction was divided into two key phases: extracting text from the property registry documents, and extracting relevant information from that text.

In the first phase, an AWS Step Function checks the document to ensure it’s in PDF format and within the expected page limit. After verification, raw data is extracted from the registry using Amazon Textract and stored in an Amazon S3 bucket.

In the second phase, another Step Function identifies the relevant fields from the raw text using Amazon Bedrock, AWS’s generative AI service. At the end of this process, results are consolidated in a structured and formal format.

This approach ensures accurate extraction and efficient workflow execution. It eliminates unnecessary document reprocessing, saving resources and time. Dividing the process into two steps also enables more precise management of the workflow in an orderly execution. This makes the client’s business more reliable in extracting property registry data, ensuring data integrity, and avoiding waste.



Benefits



The partnership with e-Core enabled scalable property registry extraction, supporting over 1,000 documents per month smoothly, meeting the client’s current objective. Previously, engineers could manually process only 15 to 30 registries per day. The average extraction time was reduced by approximately 60%, from 5 minutes to an automated 2-minute process.

As a result, the client achieved a scalable architecture for extracting property registry data and improved operational excellence through an automated workflow.


Logo: "e-core" text with a teal icon of a person with upward arrows, on a blue background.

e-Core

We combine global expertise with emerging technologies to help companies like yours create innovative digital products, modernize technology platforms, and improve efficiency in digital operations.


You may also be interested in:

Why is your frontline your strongest shield against churn?

By Adriele Radmann • August 3, 2026
Discover why customer support is your strongest shield against churn. Learn how to connect support, product dev, and AI to protect recurring revenue.

Inter's Jira Cloud Migration Saves $200K a Year

July 23, 2026
See how Banco Inter migrated to Jira Cloud, cut $200K in annual costs, and boosted team efficiency with e-Core as its implementation partner.

Why your AI tools haven't fixed alert noise yet

By Flávia Batista • July 10, 2026
There is a belief that runs deep inside IT operations teams: a noisy environment is a healthy one. If alerts are firing constantly, if tickets are piling up, if the on-call rotation is getting hit at 2am, that means monitoring is working. The tools are catching things. I understand where this comes from. In the early days of observability, silence was genuinely suspicious. A quiet dashboard often meant a gap in coverage, a misconfigured rule, something important slipping through undetected. So teams learned to treat volume as proof, and that instinct stayed long after the environment around it changed. But noise is not proof that monitoring is working. In most cases, it is proof that something upstream was never fixed. Automation at the wrong end When alert volume becomes unsustainable, the response is almost always the same. Leadership looks at the backlog (a thousand tickets a day, engineers buried, SLAs slipping) and reaches for automation at the remediation end of the pipeline: AI agents plugged into monitoring tools, scripts that fire when incident X arrives, routing logic that moves tickets faster. These are reasonable responses to an unreasonable situation, but they treat cost rather than cause. Most of those alerts should never have been generated. Processing them faster does not change why they exist.