Getting started
Introduction
See the following list for an overview of how to automate your document processing with Sensible:
- Learn to extract data from documents, or use out-of-the-box extraction support
- Integrate using Sensible's API, SDKs, quick-extract UI, or other tools
- Quality control extracted data
- Monitor and review extracted data in production
This guide gets you started with the first step, extracting data.
Learn to extract data
Let's get started with extracting document data from an example bank statement. We'll author a prompt for a large language model (LLM) to extract a checking account number in minutes.
In this guide, you'll:
- Extract data from an example document using a natural-language description of your target data, for example, a checking bank account number.
- Publish your prompt as part of a "config."
- Test your config against a second, similar document to ensure it extracts the same target data.
Get an account
-
Get an account at sensible.so. If you don't have an account, you can still read along to get a rough idea of how things work.
-
Log into the Sensible app.
-
As a new user, you complete a guided walkthrough of the steps for extracting data from documents.
View an example
-
After you complete Sensible's guided tour as a new user, navigate to a prebuilt example bank extraction at https://app.sensible.so/editor/instruct/?d=sensible_instruct_basics&c=bank_statement&g=bank_statement.
Sensible displays an example document in the left pane, and fields of extracted data in the right pane.
Take the following steps to create prompts to extract more data from the document.
Auto-extract data
To extract document data automatically, take the following steps:
-
Click Query group:
-
Click Auto generate, then click Generate:
-
Sensible automatically generates queries and extracts their answers from the document:
-
(Optional) Add more queries by clicking Suggest queries, selecting the field IDs that interest you, and clicking Add selected queries:
To test the automatically generated extraction configuration with another document, see Test the prompt. To author your own extraction configurations, see the following steps.
Manually configure extraction
Extract a table
So far, you've extracted short, simple facts. Now let's extract more complex data, such as tables and lists. To extract a table, take the following steps:
-
Click Back to fields.
-
Click Table.
-
The example already extracts the transaction history for the checking account. To extract the transaction history for the savings account, configure the table as shown in the following image. Configure a query for each column in the table, for example,
date
,description
, andamount
.
- Scroll down the right pane and click Extract. Sensible displays the extracted data.
Publish the prompt
To extract similar data from other bank statements in production, publish the "config" containing your prompt.
Click Publish configuration, click Production, then click Publish to production:
Now you've published your config, you can get document data at scale using Sensible's APIs, SDKs, or bulk-upload UI. Put the extracted data to work in Excel files, databases, and other destinations. For more information, see Integrating.
Test the prompt
Let's see if the config containing your prompt works with other bank statements. To test the prompt, take the following steps:
- Navigate to https://app.sensible.so/editor/instruct/?d=sensible_instruct_basics&c=bank_statement&g=bank_statement_2. Notice that the left pane now displays a statement for a different customer.
- In the right pane, scroll down to view the fields you authored in previous steps. Verify that the extracted data automatically updated to reflect the second example document.
(Optional) Extract from your own documents
Sensible recommends grouping similar documents, for example, bank statements, into a document type. To extract data from your documents, first check if they're on Sensible's list of out-of-the-box supported document types. If not, create document types and configure your custom extractions by using the interactive tutorial or taking the following steps:
- To exit the visual editor, click Sensible in the upper left corner.
- Click the Document types tab. Create a new document type using the dialog, then write prompts in the configuration editor to extract data using what you learned in previous steps.
Next
Learn more about extraction
- For advanced extraction strategies, see Choosing an extraction approach.
Integrate
Get extracted document data out of Sensible and put it to work in Excel files, databases, and other destinations. See Integrating.
Updated 1 day ago