Blog Articles

We're excited to announce a significant enhancement to Sensible's document extraction capabilities with the introduction of agentic LLM workflows.

Many businesses deal with PDFs containing multiple document types in a single file. These "portfolio PDFs" are common across industries and create significant processing challenges.

Learn how to write JsonLogic rules to transform your extracted document data.

Learn how to integrate human review into your document processing life cycle.

Getting data from PDFs into Salesforce can be a real challenge. For example, imagine your proptech company analyzes leases, but your company’s process for getting lease data into Salesforce is slow. With Sensible's beta Zapier integration, you can take a low-code approach to transforming data in PDFs and other documents into Salesforce records, as well as emails, databases, Google sheets, and other supported Zapier destinations.

Learn more about Human Review: a powerful new feature that allows you to easily add manual oversight to your document extraction process.

We’ve recently explored some new approaches to retrieval-augmented generation (RAG) that rely solely on completions without using embeddings. Learn how this completions-only method compares to embedding-based approaches, and why we believe it may be the future for certain RAG use cases as language models continue to improve.

Strict timelines for technological advancement are inevitably inaccurate, yet progress occurs nonetheless. Businesses need AI maturity models, not timelines, to navigate the profound industry changes that will result as AI technologies become normalized.

Explore how Sensible's SenseML streamlines Prop Tech by simplifying rent data extraction from rent rolls. This guide offers step-by-step instructions for incorporating Sensible's document extraction tools into your product.

Sensible’s new Multimodal Engine uses LLMs to extract data from non-text and partial text images embedded in a document, including pictures, charts, graphs, and handwriting.

Sensible now recommends queries to streamline onboarding your documents.

After you extract document data with our developer platform, you can use custom logic to transform the extraction to add or remove data or to conform to your desired schema.

Sensible is excited to announce native support for Excel sheets and workbooks. Excel files join Sensible’s expanding lineup of supported file types, including PDF, TIFF, JPEG, PNG, and most recently Word documents. 

Explore how Sensible's SenseML streamlines HR Tech by simplifying candidate data extraction from resumes. This guide offers step-by-step instructions for incorporating Sensible's document extraction tools into your product.

Sensible is updating its document processing system by moving from OpenAI's text-davinci-003 model to the more efficient gpt-3.5-turbo-0613, following comprehensive testing and prompt optimization.

Extract high volumes of documents (up to 5,000) at once with Sensible’s new batch extract. Upload document batches directly to the extract tab in the Sensible platform in bulk, eliminating manual file-by-file efforts.

Use Sensible’s Node SDK to directly integrate Sensible’s document extraction and classification APIs into your product.

With new format support for Microsoft Word, you can now use Sensible to extract .doc and .docx files. Send your .doc or .docx file to any Sensible endpoint or upload directly to the Sensible app as usual.

Explore the remarkable history of the PDF. This ubiquitous format, which has shaped the way we share and view documents, has a story as compelling as its widespread use. Discover why the PDF, often criticized yet universally used, continues to be a vital part of our digital world in 2023.

This tutorial guides you through the process of creating a Python application using the GPT-3 model and testing it with several text-heavy tasks, such as summarizing text, fleshing out outlines, and writing content.

Sensible’s new user management capabilities make it easy to coordinate your team’s account directly within the Sensible app.

Converting PDF files to Excel makes the content of documents and forms more accessible to spreadsheets’ data wrangling (filtering/querying) capabilities.

Enhance your Python skills by learning six different file uploading techniques. This guide includes everything from using the requests library to setting up a Django web app for uploads.

Optimize LLMS for for document question answering: chunking, layout preservation, cost optimization, and confidence scores.

This tutorial guides Python developers through the process of extracting structured text from PDF documents using Sensible, a developer-first platform. The guide explains the step-by-step process of creating a configuration with SenseML, Sensible's document query language, retrieving the API key, and writing Python script to call Sensible's extractions API, thus showcasing Sensible's efficiency over alternatives like manual data entry or traditional OCR tools.

We’re excited to announce the launch of Sensible’s in-app dashboard. Now, you can track all your document extraction metrics in one place, in real-time. Easily aggregate performance summaries, monitor configuration success, track usage at the document type level, and view historic performance data for all production deployments.

We’re excited to announce the launch of Sensible’s confidence signals for our natural language methods. Confidence signals gauge the accuracy of LLM extractions similar to how machine learning models use confidence scores.

Sensible’s new classification API automates document identification, labeling, and routing without needing any additional configuration.

Today, we're thrilled to launch Sensible Instruct, a document understanding tool powered by LLMs, including GPT-4. With Sensible Instruct, you use natural language to instantly extract data from any document, even ones you’ve never seen before. Resumes, invoices, contracts, academic research, bank statements, utility bills and more – Sensible Instruct can parse them all.

While Daylight Saving Time may have stolen an hour of sleep this weekend, Sensible’s new natural language processing (NLP) capabilities, bulk CSV downloads, and OCR confidence scores will give you back that time (and then some).

Use SenseML to extract structured data from bank statements.

Getting data from PDFs into existing databases can be a real challenge. For example, imagine your proptech company analyzes mortgage applications, but your company’s process for getting data from 1040 forms into databases is really slow. With Sensible's beta Zapier integration, you can take a low-code approach to transforming data in PDFs and other documents into emails, databases, Google sheets, and other supported Zapier destinations.

As Christmas approaches, the elves at the North Pole are busy preparing for the big day. For years, Santa has relied on a team of elves to manually enter data from the millions of wish lists that children send to the North Pole. But this year, Santa decided to try something new and enlisted the help of Sensible, a powerful tool for extracting structured data from documents, even ones handwritten in crayon.

Craft Ventures leads the round, with participation from Engineering Capital and Clocktower Technology Ventures. Learn more about Sensible's vision for the future.

Use SenseML to extract structured data from a Medicaid explanation of benefits PDF.

Learn how you can quickly extract a document (No API Required™), access and clone over 100+ configurations directly in the Sensible dashboard, and rearrange the fields across different sections in your output.

Use SenseML to extract structured data from a mortgage loan closing disclosure PDF.

We may have been a tad quiet recently but it's not because we were on summer vacation – we've been hard at work over the last few months on a number of new features while continuing to improve the platform with updates to the SenseML Editor and API. In this update, learn about how we’ve added support to convert PDFs to Excel, revamped the editor, enriched the API and PDF metadata, and enhanced our existing SenseML methods.

Documents remain underused in software toolchains, and valuable data languish in PDFs. The challenge has shifted from identifying text in documents to turning them into structured data suitable for direct consumption by software-based workflows or direct storage into a system of record. The best way to turn the vast majority of documents into structured data is to use a next generation of powerful, flexible templates that find data in a document much as a person would.

Today we are pleased to announce custom region support for our Enterprise customers. Businesses outside the US with data residency requirements, and businesses that would like to minimize latency to Sensible's API, will now be able to select their preferred AWS region. 

Extract structured data from natural-language, free-text documents like leases and legal contracts with Sensible using GPT-4.

Use SenseML to extract structured data from a trucking rate confirmation PDF.

Learn SenseML with our new interactive walkthroughs after you sign up for a free Sensible account.

Extract useful data from personal PDFs, like old bank statements or gas bills, with Sensible

Loss runs are full of valuable information about an entity's risk profile, but the density of information means that there's more room for human error if you're relying on manual data entry. Learn how Sensible handles a loss run's complex structure to extract clean, tabular data automatically.

Mortgage underwriting portfolios, with multiple documents per PDF, present unique challenges for data extraction. We show how to overcome those challenges.

Get up and running on Sensible in minutes using our pre-built configurations for common document types.

Use these techniques to minimize your extraction times.

Discover how Marble used Sensible to get to 2,000 members and $2MM of tracked premiums with just one ops person.

Use SenseML to extract structured data from the ACORD 25, a certificate of liability insurance.

Use these techniques to avoid the time, cost, and accuracy drawbacks of OCR.

Learn how Inspectify reduced the time it took for their team to process a home inspection report from 15 minutes to 5 using Sensible.

There is a lot to like about paper documents and PDFs. They're easy for people to use and understand. Businesses use them to work with other businesses without pre-planning and coordination. Some documents are even elegant in their design and their representation of data. But as software eats the world, these documents are a major cause of indigestion.