Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
- Learn how to choose and configure generative AI guardrails in Azure AI Foundry.
By the end of this module, you'll be able to:
- Configure filters and threshold levels to block harmful content.
- Perform text and image moderation for harmful content.
- Tune thresholds by analyzing the Precision, Recall, and F1 score metrics.
- Detect groundedness in a model's output.
- Mitigate direct and indirect prompt injections.
- Export starter code that reflects your filter configurations.
- Learn how to implement generative AI guardrails 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 model's output.
- Identify AI-generated text that matches known protected text.
- Detect direct and indirect prompt attacks with Prompt Shields.
- Learn how to measure and mitigate risks for a generative AI app leveraging responsible AI tools and features within Azure AI Foundry.
By the end of this module, you're able to:
- Choose and deploy a model from the model catalog
- Upload data and create a vector index
- Set up and refine a system message
- Create and apply a content filter
- Run a manual evaluation
- Run and compare automated evaluations
