- Module 1: Learn how to choose and build a content moderation system in Azure AI Studio.
By the end of this module, you're able to:
- Configure filters and threshold levels to block harmful content.
- Perform text and image moderation for harmful content.
- Analyze and improve Precision, Recall, and F1 Score metrics.
- Detect groundedness in a model’s output.
- Identify and block AI-generated copyrighted content.
- Mitigate direct and indirect prompt injections.
- Output filter configurations to code.
- Module 2: Learn how to choose and build a content moderation system with Azure AI Content Safety.
By the end of this module, you're able to:
- Perform text and image moderation for harmful content.
- Detect groundedness in a models output.
- Identify and block AI-generated copyrighted content.
- Mitigate direct and indirect prompt injections.
- Module 3: Learn how to measure and mitigate risks for a generative AI app leveraging responsible AI tools and features within Azure AI Studio.
By the end of this module, you're able to:
- Upload data and create an index
- Set up a system message
- Create and add a content filter
- Execute a manual evaluation
- Execute and analyze an AI-assisted evaluation
Operationalize AI responsibly with Azure AI Studio
Overview
Syllabus
- Module 1: Module 1: Moderate content and detect harm in Azure AI Studio with Content Safety
- Introduction
- Content Safety
- Prepare
- Harm categories and severity levels
- Exercise – Text moderation
- Exercise – Image moderation
- Exercise – Groundedness detection
- Exercise – Prompt shields
- Exercise – Integrate with the Contoso Camping Store platform
- Knowledge check
- Summary
- Module 2: Module 2: Moderate Content and Detect Harm with Azure AI Content Safety
- Introduction
- Azure AI Content Safety
- Prepare
- Harm categories and severity levels
- Exercise - Text moderation
- Exercise - Image moderation
- Exercise - Groundedness detection
- Exercise - Prompt shields
- Exercise - Integrate with the Contoso Camping Store platform
- Knowledge check
- Summary
- Module 3: Module 3: Measure and mitigate risks for a generative AI app in Azure AI Studio
- Introduction
- Prepare
- Choose and deploy a model
- Upload data and create an index
- Create a system message
- Create a content filter
- Run a manual evaluation
- Run and compare automated evaluations
- Knowledge check
- Summary
