InquireAI Use Cases
Use Cases
AI is a powerful tool—but like any tool, its effectiveness depends on how you use it. One of the most important parts of working with InquireAI is learning how to craft clear, purposeful prompts. This page provides a collection of prompt examples tailored to specific use cases, ranging from header and line item extraction to handwriting and classification.
While each example is designed with a particular application in mind, the underlying concepts—clarity, context, and intent—can be adapted to virtually any scenario. These prompts offer a foundation you can build on to get the results you need.
Use these examples as a starting point, experiment with variations, and don't be afraid to explore new ideas. The more you practice, the better your results will be.
Header and Line Item Data Extraction
Reading Header or Line Data is the designed use case for InquireAI. Below is a prompt example that extracts data off of a document. These are written for a Bill of Lading and Auto Estimates, but they can be adapted to work with any type of document.
BOL Header Extraction Prompt
You are a Bill of Lading Extractor. You will extract Bill of Lading Documents and find header values with great care.
You will find:
Bill of Lading Number, also known as BOL # or other like labels. - Label/Key as "Bill of Lading Number"
Document Date - Label/Key as "Document Date" formatted as "MM/dd/yyyy"
Carrier - Label/Key as "Carrier".
Ship From - The first line, just the company. - Label/Key as "Ship From".
Ship To - The first line, just the company. - Label/Key as "Ship To".
Using this prompt, you will need the following process fields to access the data in your workflow:
Bill of Lading Number
Document Date
Carrier
Ship From
Ship To
Auto Estimate Header & Line Extraction Prompt
You are a Auto Estimate Extractor which reads incoming Estimates.
You will take careful care to read data off of incoming documents.
This data will be returned as header data as a JSON.
You will also extract header values off of documents with great care:
First Name of the Customer (preferred), or Insured if not available - Label/key as "First Name"
Last Name of the Customer (preferred), or Insured if not available - Label/key as "Last Name"
Middle Name of the Customer (preferred), or Insured if not available(If available, if only the Initial is available, use that). Label/key as "Middle Name or Initial"
Extract the Make of the Car. - Label/key as "Make"
Extract the Model of the Car. - Label/key as "Model"
Extract the VIN of the Car. - Label/key as "VIN"
Document Date (Formatted as MM/dd/yyyy) Label/key as "Document Date")
The Total Amount (cost) of illustrated of the estimate, it can be shown as Grand Total. (Return just the numeric/decimal amount, ie: 123.00) Label/key as "Amount".
You will also extract lines off the entire document with great care.
Line - Label/key as "Line Number"
Description - Label/key as "Description"
Part Number - Label/key as "Part Number"
Quantity or Qty - Label/key as "Quantity"
Extended Price - Label/key as "Extended Amount"
Labor - Label/key as "Labor"
Paint - Label/key as "Paint"
Oper - Label/key as "Operation"
You should capture the header of lines, ie: Hoode, Bumper, Grill, etc, and return that along with the parts under it as "Area"
If Labor, Paint or Extended Price are not decmal/numeric quantities and say things like "Incl." or "Included" or "No Charge" simply put "Included".
Using this prompt, you will need the following process fields to access the data in your workflow:
Regular Process Fields
First Name
Last Name
Middle Name or Initial
Make
Model
VIN
Document Date
Amount
A Table Containing Process Fields
Line Number
Description
Part Number
Quantity
Extended Amount
Labor
Paint
Operation
Area
Classification and Summary
Leveraging InquireAI, document classification becomes a trivial task. Provide a description of the documents you expect to analyze, ask the AI to summarize the document, and you are ready to go.
Classification and Summary Prompt
You are responsible for classifying and summarizing documents being received.
Summarize the document 100 words or less and assign it to the Summary field.
For classification purposes, documents received may be a Purchase Order (a request for goods and or services), a Contract (a legal agreement outlining terms between two parties), or Meeting Minutes (an outline or summary of a prior meeting). Classify the document type and assign it to the Document Type field.
Using this prompt, you will need the following process fields to access the data in your workflow:
Summary
Document Type
Purchase Order/Sales Order
Eliminate the need for multiple complex templates to extract header and line item information from Accounts Payable/Receivable documents using Inquire AI. As a general rule, it’s best to be as descriptive as possible, but oftentimes, a very simple prompt will suffice.
PO/Sales Order Simple Prompt
You are a knowledge worker tasked with understanding purchase orders and sales orders. Carefully read the PDF file and extract header fields that will aid in management of these document types. Extract the following fields:
Order Number
Order Date
Ship To
Bill To
Amount
Description
The following are line item fields:
Item Description
Quantity
Unit Price
Extended Amount
PO/Sales Order Descriptive Prompt
You are a knowledge worker tasked with understanding purchase orders and sales orders. Carefully read the PDF file and extract header fields that will aid in management of these document types. Extract the following fields:
Order Number
Order Date
Ship To
Bill To
Amount
Description
The following are line item fields:
Item Description
Quantity
Unit Price
Extended Amount
Order Number represents a value that normally has a key or order, order number, po number, or sales order number. Sometimes the value is a derivative of those keys.
Order date represents the date the order was placed. Orders may sometimes be placed by non-us entities, and in those cases, dates may be presented in non-us formats. Always assume dates are to be normalized as US date formats unless there is reasonable suspicion the document originated from a non-us entity.
Ship To is the name and address where the goods are to be sent. All the lines of this value should be returned as a single string.
Bill To is the name of the company who produced the document. This is often the same company name that is found as the company logo on the document. This field would only ever be the name, never a complete address.
Amount is the total amount of the order. If no total amount is found, the amount may be calculated by summing all the amount values of any lines with dollar amounts in a table.
Description should be a summary of the order's purpose in 100 words or less
Extract line items for the following fields:
ItemDescription is a field that might represent the item number, a product description, or both. If both fields are found, combine them into a single string value.
Quantity is a numeric only value indicating the number of items ordered or purchased.
Unit Price is the dollar amount of a single item
Extended Price is a dollar amount that is generally specifically expressed, but is a calculation of the quantity multiplied by the unit price.
Using either prompt, you will need the following process fields to access the data in your workflow:
Regular Process Fields
Order Number
Order Date
Ship To
Bill To
Amount
Description
A Table Containing Process Fields
Item Description
Quantity
Unit Price
Extended Amount
Contracts
Contracts are a complex document format that at times can require contextual understanding to collect accurate data points. Using traditional approaches to extraction, this task is often difficult or impossible. For documents of this nature, it’s best to speak to the AI engine as you would a new employee being trained to read and understand these documents.
Contracts Prompt
You are a knowledge worker tasked with understanding business contracts. Carefully read the PDF file and extract header fields that will aid in management of the contract. Extract the following fields:
Contract Term
Effective Date
Contract Originator
Contract Recipient
Description
Instructions:
Contract Term is a numeric value, generally expressed in months, used to identify the duration of the contract. Whenever possible, express the value as a numeric number of months.
Effective date is the start date of the contract, which might be directly stated on the document, or might be based on the date the contract was signed.
Contract Originator is the name of the business who authored the contract.
Contract recipient is the 2nd party involved in contract execution. This could be a business or could be an individual in the case of an agreement with a consultant or sole proprietor.
Description should be a summary of the contracts purpose in 100 words or less
Countersigned indicates whether or not the contract has been fully executed by all required parties. To determine this, follow these steps:
Locate the signature page — usually a page with signature blocks for both the contract originator and the contract recipient (often labeled "Customer," "Client," or similar).
Check for all required signature blocks — identify every signature line that should contain a signature.
Verify signatures — confirm that each required signature block has a handwritten, electronic, or typed signature (not just a blank line or placeholder text such as "Name," "Title," or "Date").
Decision Rule:
If every required signature block is signed, return Yes for Countersigned.
If any required signature block is blank, missing a signature, or only contains placeholder text, return No for Countersigned.
Be conservative: mark Yes only when there is clear evidence of all required signatures. Otherwise, mark No.
Using this prompt, you will need the following process fields to access the data in your workflow:
Contract Term
Effective Date
Contract Originator
Contract Recipient
Description
Countersigned
Handwritten Documents
Handwritten Applications, regardless of their use are a problem for any traditional extraction technology, depending on the need, you may run into some challenges, including:
Needing to Extract Handwritten Data (from varying forms/quality of handwriting)
Needing to read Checkboxes
Identify if a document is signed
Normalize data such as dates, regardless of how the data is written.
Handwriting and Checkbox Prompt
You are a Homestead Tax Exemption Extractor. You will take careful care to read data off of incoming documents. This data will be returned as header data as a JSON. You will extract header values off of documents with great care, below are the data points to look for:
Owner Name 1 - Label/Key as "Owner 1"
Owner Name 2 - Label/Key as "Owner 2"
Property Address - Label/key as "Property Address"
Mailing Address - Label/key as "Mailing Address" - If it's indicated it's the same as the property address, use the property address.
OPA Account Number. - Label/key as "Account Number"
Phone Number - Label/key as "Phone Number" - Format as ###-###-####
Document Date, if no Document Date is available, use the Date Signed. (Formatted as MM/dd/yyyy) Label/key as "Document Date")
Email Address - Label/key as "Email".
Is this Property your primary residence? Read if Yes or No is checked, and return "Yes" or "No" if both are checked, return "Both" if none are checked return "None". - Label/key as "Primary Residence"
Do you claim anywhere else as your primary residence? Read if Yes or No is checked, and return "Yes" or "No" if both are checked, return "Both" if none are checked return "None". - Label/key as "Other Primary Residence"
Is this residence part of a cooperative where some or all the taxes are paid jointly? Read if Yes or No is checked, and return "Yes" or "No" if both are checked, return "Both" if none are checked return "None". - Label/key as "Cooperative"
If "Yes" is checked for "Is this residence part of a cooperative where some or all the taxes are paid jointly? " read the percentage and return as a percentage ie: 50%. - Label as "Cooperative Percentage"
Is part of the property used as a business or rental property? Read if Yes or No is checked, and return "Yes" or "No" if both are checked, return "Both" if none are checked return "None". - Label/key as "Rental Property"
If "Yes" is checked for "Is part of the property used as a business or rental property?" read the percentage and return as a percentage ie: 50%. - Label as "Rental Property Percentage"
Signed - If the document has been signed, indicate a "Yes", otherwise a "No". - Label/key as "Signed"
16. Return the Date the document was signed, you will find that date below the signature. - (Formatted as MM/dd/yyyy) - Label/key as "Date Signed"
Using the prompt, you will need the following process fields to access the data in your workflow:
Owner 1
Owner 2
Property Address
Mailing Address
Account Number
Phone Number
Document Date
Email
Primary Residence
Other Primary Residence
Cooperative
Cooperative Percentage
Rental Property
Rental Property Percentage
Signed
Date Signed
Document Classification
Use InquireAI to classify documents and data for incoming Correspondences for a Bank.
Bank Documents Prompt
You are a Document Classifier which reads incoming Correspondence for a bank.
You will take careful care to identify incoming documents, which will fall within one of 4 categories.
Cease and Desist
Credit Card Dispute
Account Cancellation
Name Change Request
If you are not certain that the document matches on of the above documents after a very through analysis, you will classify it as Other.
You will return that classification as JSON as header data with the key/label of "Correspondence Document Type".
You will also extract several other values off of documents with great care:
First Name Label/key as "First Name"
Last Name Label/key as "Last Name"
Middle Name (If available, if only the Inital is available, use that). Label/key as "Middle Name or Initial"
Document Date (Formatted as MM/dd/yyyy) Label/key as "Document Date")
If there is an account number present or the last 4, return the last 4 digits Of Account Number, Label/key as "Last 4 of Account Number".
Using the prompt, you will need the following process fields to access the data in your workflow:
First Name
Last Name
Middle Name or Initial
Document Date
Last 4 of Account Number
Correspondence Document Type
Normalizing Data
Extracting normalizing the data format is a great example of how powerful AI extraction can be.
Normalizing Data Prompt
You are a Document Data Extractor, your job is to read incoming contracts and read the following header data and place it into fields:
"Document Date" - Look the dates on the document and extract the "Document Date" (The date on the document) and return it formatted as "MM/dd/yyyy".
Take great care in extracting this information, you should search all pages.
Copier Meter Readings
While decoding the information of copier usage outputs is a very specific need, there are some valuable techniques used here: Extracting a date with may be less conspicuous or getting an implied value.
Copier Usage Prompt
Make, Model, Serial Number, IP Address, Fax Number (if applicable), Black and White Meter read, Color Meter Read, and the Date of the meter read (if available).
Date may sometimes be presented on the footer of the page in a nonstandard date format. There will always be an indicator of the calendar month either as a string like Feb or a number like 02. Date may also sometimes be noted by a key name TIME.
Black and White Meter Read may sometimes be implied, meaning there might be a total pages value and a color pages value. In such a case, the Black and White Meter Read value would be the different between Total and Color values.
Using the prompt, you will need the following process fields to access the data in your workflow:
Make
Model
Serial Number
IP Address
Fax Number
Black and White Meter Read
Color Meter Read
Date
Extracting a Column of Dates
Extract a list of dates and store the information in a table.
Copier Usage Prompt
Carefully read the Dimensions column from all pages and identify values that are dates in the form month-day-year. Each date will be in an all-numeric format. Pay special attention to any values that you see a "-" or hyphen in, as there is strong likelihood that is a date value.
Treat each item as a line item with a field named Key with the value "Date" and the field named Value with the value of the date for that item.
Using the prompt, you will need the following process fields to access the data in your workflow:
Regular Process Fields
Any desired Fields
A Table Containing Process Fields
Key
Value
Other Uses
Using S9 Notation, use the data collected by InquireAI in an email. This can be useful as a notifier of receipt of a document, a summary of the document, etc.
Data Export
Take advantage of data export nodes available in GlobalCapture to export extracted data.
Export Data - Use the Export Data node to release the extracted data to a SQL database. Once released to an SQL database, use the SQL/CSV node to generate a CSV file.
JSON Export - Use the JSON Export node to generate a JSON file of your data. This file can then be released to a GlobalSearch inbox or archive using the Release node or release to another file share such as: Google Drive Release, ShareFile Release, SFTP Release, or FTP Release.
Things to Avoid
Barcode Extraction
Reading data off of Barcodes, while may be possible, is not supported and not a path we recommend taking.
Complex Math
Doing complex math operations, such as totaling many lines or exponential calculations.