Security audit records get created when a prompt runs and a response gets back from AI. These records help identify the data we send and receive.
Feedback after running a prompt also gets tagged to these records. These records will host the error messages that are encountered when we run GPTfy, too.
Identifying Important Tabs and Fields in Security Audit Records
Understand the critical tabs and fields within these records to capture essential information.
Details Tab:
- AI Prompt: View the prompt that triggered the creation of this record.
- Prompt Command: Specific command associated with the prompt.
- Message: Capture any error messages associated with the prompt execution.
- Record ID: Identify the unique record ID linked to the prompt execution.
- GPT Config: It shows which connection has been used.
- Prompt Tokens: It shows the Initial input text provided to the AI model to generate a response.
- Completion Tokens: It is the Tokens generated by the AI model as part of its response
- Total Tokens: Total number of tokens used in generating the AI response.
- Pre-Processing Time: This is the time taken to extract the data in seconds.
- Processing Time: This is the time AI takes to process the response in seconds.
- Post-Processing Time: This is the time taken for presentation, i.e., displaying the result in the field AI Response Processing or updating the Target Field.
- Total Response Time: This is the overall response time in seconds, which is the sum of Pre-processing time, Processing Time, and post-processing time
- Context Tab:
- Data (PII Key): The encryption key to process Personally Identifiable Information (PII).
- Data (Original): The raw data extracted from Salesforce.
- Data (PII Removed): Review the data processed to remove PII and transmit it to the AI.
- The context tab has the option to View in the JSON Viewer. The Data Original and the Data PII Removed are available in JSON format, which allows users to view and analyze the JSON (JavaScript Object Notation) data in a user-friendly manner.
- Response Tab:
- Data (Decrypt PII Key): Decrypting key to reintroduce PII into the data.
- AI Processed Data (No PII): Examine the response after data deidentification.
- AI Processed Data (PII Added): Review the response received from the AI, now including PII.
- The response from the Console will be populated at the top of the Response tab of the security Audit record.
- Feedbacks Tab:
- Access a list of feedback related to a specific response.
- Feedback is captured through the thumbs-down icon on the GPTfy console, allowing users to provide suggestions if they have any.
- This feedback is associated with responses and linked to the respective audit record.
Feedback can be added via the GPTfy console, and here is the step-by-step procedure on how to provide feedback on a particular response and how it gets mapped to the security audit record.
- Files – When the user provides huge characters to the AI and after running the prompt, if Data Original contains more than 131072 characters then it creates the 2 files.
Data_PII_Removed__c
Data_Original__c
Step 1: Run a prompt
- Run a prompt on a record.
- Response gets pasted to the console and a Security audit record is created.
Step 2: Give a Feedback. For example – Thumbs-up
Click on the Thumbs-down icon in the console.
Add Comments and select any available options.
- Click Save.
Step 3: Verify the feedback
- Open the security audit record by click on the hyperlink on the console.
- Click on the feedback tab.
- A related record of feedback is added.
