Using AI 거버넌스 dashboard widgets
- 최종 업데이트2024/10/03
Using AI 거버넌스 dashboard widgets
Enhance your AI 거버넌스 dashboard experience by reviewing data for AI를 활용한 최고의 자동화, 가장 많이 사용되는 모델, and 토큰 소비 widgets to view, monitor, and analyze AI data derived from model interactions during automation development and automations executions across your enterprise.
Permissions
AI를 활용한 최고의 자동화 widget
This dashboard widget displays a bar graph showing the top ten frequently run automations that uses AI interactions. You can see the name of the top ten automations and their number of executions in the Last 24 hours. Hovering over an automation bar in the widget shows you a blurb with the automation name and the total number of execution runs.
Drill-down:
Click a bar graph to drill-down and view additional details. Clicking an automation bar navigates you to the tab in the Control Room where you can view a list of all the executions the automation ran listed by sessions. Clicking each sessions displays the details. You can change the time filter in this screen.
See, AI 프롬프트 로그 상호 작용 모니터링.
가장 많이 사용되는 모델 widget
The GRC Lead and Automation Lead would use this widget to monitor and track the 모델 활용 for the 가장 많이 사용되는 모델 within automations to effectively manage subscriptions. This will help them implement the use of approved and supported models from the hyperscaler vendors.
The 가장 많이 사용되는 모델 widget gives visibility into the most popularly used top five models within automations using the 생성형 AI 패키지 and AI Skill: 패키지to execute automations in the Production environment.
- The automation name with the package used, whether it used the 생성형 AI 패키지 or the AI Skill: 패키지
- The model used from the hyperscaler vendor, for example: GPT-4 from OpenAI
Hover over a bar to see a summary of the details.
Drill-down:
Click a bar graph to drill-down and view additional details in addition to the entire list of the most used models from hyperscaler vendors. Clicking the bar navigates you to the tab in the Control Room where you can view a list of logs filtered by the model name. The logs are displayed by Event type. Click an Event type to view additional details for the model interactions that took place within the automation execution.
See 이벤트 로그 모니터링.
- In addition to the drill-down option from the bar graph, click the ellipses at the top-right corner to select View details for a detail view.
- The AI 거버넌스 dashboard screen displays the 모델 활용 tab details.
The 모델 활용 details view for the 가장 많이 사용되는 모델 displays the top five automations in the visual, in addition to the entire list of automation details in the table as follows. You can change the time filter in this screen.
Export reports based on the data represented in the widget by clicking or on your screen.
| Column header | Description |
|---|---|
| Model name | This is the model used in a specific automation such as
GPT-4 from OpenAI. You can click
the model to go to tab in the Control Room
where you can view all logs filtered by the model
name. See 이벤트 로그 모니터링. |
| Publisher | Supported hyperscaler vendor such as Amazon Bedrock, Google Vertex AI, Azure OpenAI, or OpenAI. |
| Automations | Number of 생성형 AIcommand actions used in automation executions using the 생성형 AI 패키지 and AI Skill: 패키지. |
| AI Skill: | Number of calls automations executed using AI Skill:. |
| Model calls | Number of calls made to the model. |
| Devices | Number of devices used during the model interaction. |
토큰 소비 widget
The 토큰 소비 widget provides visibility into your top automations consuming most number of tokens aggregated per model. To derive the total count for a model's 토큰 소비, the metrics is calculated based on the Automation name, Folder path, and the model name from the hyperscaler vendor. Hover over a bar in the widget to see the 토큰 소비 details of a specific automation.
By default, the 토큰 소비 widget shows data for the Last 24 hours which can be changed to a different time filter in the widget details screen.
The GRC Leads and Automation Leads would use this widget to monitor and track the token usage of the models during their interactions and execution within automations to effectively manage cost and subscription. This will help them project 토큰 소비 based on model preference.
- Navigate to the ellipses at the top-right corner of each widget and click to select View details for a detail view.
- The AI 거버넌스 dashboard screen displays the 토큰 소비 tab details.
The 토큰 소비 details view displays the top five automations in the visual, in addition to the entire list of automation details in the table as follows. You can change the time filter in this screen.
Export reports based on the data represented in the widget by clicking or on your screen.
| Column header | Description |
|---|---|
| Automation name | Name of the automation that was executed. You can click the name to go to tab in the Control Room where you can view all logs filtered by the automation name. |
| Folder path | The folder location of the automation from where it was executed. |
| Publisher | Supported hyperscaler vendor such as Amazon Bedrock, Google Vertex AI, Azure OpenAI, or OpenAI. |
| Model name | This is the model used in a specific automation such as GPT-4 from OpenAI. |
| Users | Number of users. |
| Workspace | This can be the Private or Public folder from where the automation was executed. |
| AI Skill: | Number of AI Skill: used in the automation. |
| Tokens | Total token count used by the model. |
You can export reports based on the data represented in the widget by clicking or on your screen.