AI Governance updates
- Updated: 2024/12/26
This topic outlines the key enhancements made to the AI Governance framework following the introduction of AI Guardrails.
AI prompt log updates
A new column AI guardrail is introduced to the AI prompt log table and it will show the guardrail applied to each of the sessions.
 |
Duration: Shows the start and end time of a session
execution.
Note: This information
is not available if the session is in
progress. |
 |
Start time: Shows the start time of the session execution. |
 |
Session ID: Shows the session ID for an automation execution. A session can consist of multiple model interactions, which are part of the same automation execution. Click the Session ID link to view details of all model interactions for that session. |
 |
Prompt type: Shows the type of prompt used in the automation. For example, Free Form is relevant when Generative AI packages are used or Prompt Template is relevant when Generative AI Prompt Template packages are used. |
 |
Automation name: Shows the automation name that used the prompt. |
 |
Device name: Shows ID of the device on which the
automation was executed.
Note: This
information is not available if the action was performed
in the Control Room. |
 |
User: Shows the ID of the user who ran the automation. |
 |
AI guardrail: Shows the specific Guardrail applied to each AI session. |
 |
Folder path: The folder location of the automation from where it was executed. When an AI Skill is integrated with an automation (parent or child), the folder path displayed is the same as the folder path of the parent automation. |
From the AI prompt log table, you can click the Session ID link to drill-down further to view details of a session.
You can view the model interaction session details in the same screen by expanding the foundational model name displayed for that interaction. Click the prompt or action in the details section to view more details of the prompt or model responses.
- AI guardrail assigned: Displays the specific Guardrail applied to each AI session.
- Toxicity: Displays the toxicity level of the prompt and response.
For more details about the monitoring AI prompt log interactions, see Monitor AI prompt log interactions.
Event logs updates
A new column AI guardrail is introduced to the Event logs table and it will show the guardrail applied to each of the events.
|
Status: Shows the success or failure of an event. |
|
Time: Shows the start time of the event. |
|
Event type: Shows each session type such as: Send prompt, Response received, Model connection, and Trigger prompt template. You can click the Event type link to drill-down and view additional event details. |
|
Model name: Shows the foundational model version name that was interacted with, such as: Claude for Amazon Bedrock, VertexAI forGoogle Vertex AI, GPT 3.5 Turbo for Azure OpenAI, and others. |
|
Prompt type: Shows the type of prompt used in the
automation. These are:
|
|
Automation name: Shows the automation name that used a specific prompt. |
|
Session ID: Shows the automation session ID. |
|
Device name: Shows the ID of the device on which the automation was executed. |
|
User: Shows the ID of the user who ran the automation. |
 |
AI guardrail: Shows the specific Guardrail applied to each event. |
 |
Folder path: The folder location of the automation from where it was executed. |
- Model connection
- Send prompt
- Response received
- Trigger Prompt Template
In the Event type column, click the link to drill-down further to view event details by the following parameters. The details vary as per event type. On the same screen, view different parameters for each event type.
- AI guardrail assigned: Displays the specific Guardrail applied to each AI session.
- Toxicity: Displays the toxicity level of the prompt and response.
For more details about the monitoring Event log, see Monitor Event log interactions.