Sensible Instruct authoring tips

Configure low-code document data extractions using Sensible Instruct, powered by large-language models (LLM) such as GPT-4.

Sensible Instruct is a low-code, AI-powered subset of SenseML, Sensible's JSON-based document extraction query language. By combining Sensible Instruct and SenseML, you can extract data from a range of document types, from highly structured business forms to unstructured research documents.

See the following topics for tips on configuring extractions in Sensible Instruct:

MethodExample use caseNotes
List methodFor each vehicle in an auto insurance declaration, extract the VIN, model, and year.Extracts a list of data out of a document, where you don't know how the data are represented.
NLP Table methodFor each transaction in a bank statement table, extract the date and amount.Extracts a list of data out of a document, where you know they're in a table.
Query method"When does the policy period end?"
"What are the last 4 numbers of the account?"
Extracts a single fact or data point.

Notes

For layout-based extraction methods, see methods.