Loan Processing with Azure OpenAI > Using the Loan Processing with Azure OpenAI recipe > Step 7: Invoke the process
  

Step 7: Invoke the process

You can invoke the Process Loan Request LLM process to evaluate a loan request and approve or reject it based on the applicant's credit score by using one of the following options:

Publishing and running the Guide

Publish and run the guide and enter the required details on the screens.
  1. 1Open the Loan Processor guide.
  2. 2On the Start tab of the Start step, ensure that the Run As field is set to Current User.
  3. 3Save and publish the guide.
  4. 4On the Actions menu, click Run. Alternatively, you can copy the execution URL from the Properties Details dialog box to run the guide.
  5. 5On the Instructions page, enter information related to personal details, employment details, and loan details, and attach an identity proof. The LLM uses this information to perform initial verification.
  6. 6Click Submit Loan Request.
    7. If the credit score of the applicant is more than 600, the loan gets automatically approved and an approval email is sent to the applicant with the document for an e-signature. Otherwise, an email is sent to the applicant stating that the loan application is under review. Simultaneously, an email is sent to the reviewer to review the loan request. Based on the reviewer's decision, if the loan is approved, an approval email is sent to the applicant with the document for an e-signature. Otherwise, a loan rejection email is sent.
  7. 7On the next screen, the load ID and loan status appear.
  8. 8Click Continue.
  9. 9Click Done.
You can also use the embed code to embed the guide into an HTML document of a third-party application.
Note: If you encounter any issue with loading the guide, check whether you are using the default guide theme.

REST or SOAP API endpoints

Pass input through REST or SOAP API endpoints in any API client such as cURL, Postman, SOAP UI, or through any programming language.
For example:
  1. 1Open Postman.
  2. 2Select the HTTP verb as POST and specify the generated REST service URL and payload as shown in the following image:
    3. The image shows the HTTP verb, REST service URL, and the request payload.
    Here is the sample payload:
    {
    "LoanRequest": {
    "employmentDetails": {
    "jobTitle": "Developer",
    "employerName": "PM",
    "monthlyIncome": "10000"
    },
    "customerID": "12354",
    "loanPurpose": "home improvement",
    "personalDetails": {
    "lastName": "Pmd",
    "firstName": "FirstName",
    "address": {
    "city": "Texas",
    "street": "Street",
    "postalcode": "563210",
    "state": "State"
    },
    "phone": "9999999999",
    "email": "pram@gmail.com"
    },
    "loanAmount": "2000",
    "ssn": "12323274387823"
    },
    "LLM_Settings":
    {
    "Top_P": "1",
    "Temperature": "0.9",
    "Max_Tokens": "300",
    "Deployment_ID": "cai-qa-gpt4turbo-sweden",
    "API_Version": "2024-06-01"
    }
    }
    Optionally, you can configure the LLM settings properties in the Set LLM properties step in the Process Loan Request LLM process. For more information, see Step 6: Publish the processes. If the LLM settings properties are preconfigured in the Process Loan Request LLM process and you also enter them as input in the request payload, the request payload values take precedence.
  3. 3Enter the user account details on the Authorization tab.
  4. 4Click Send.

Run Using

Pass input in the JSON or XML format through the Run Using option of the process.
  1. 1Open the Process Loan Request LLM process and click Actions > Run Using.
  2. 2Click New Input, enter a name for the process input, and click Save.
    3. The payload is populated in the Process Input section.
  3. 3From the Encoding list, select JSON or XML based on the format that you want to work with.
  4. 4Enter the values for the process object fields in the payload.
  5. 5Validate, save, and run the process.