Join Devanshi Thakar and Wayne Smith as they dive into the essentials of building solutions with Responsible AI (RAI) in Azure. This video covers a use case from Contoso Health, showcasing how to enhance patient engagement with an AI-powered support system. Learn about Microsoft's ethical AI principles and key Azure services that ensure your solutions are fair, reliable & safe, secure, inclusive, transparent, and accountable.
RESOURCES
- RAI Principles: https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/strategy/responsible-ai
- Responsible AI Impact Assessment Template: https://blogs.microsoft.com/wp-content/uploads/prod/sites/5/2022/06/Microsoft-RAI-Impact-Assessment-Template.pdf
- EntraID: https://learn.microsoft.com/en-us/entra/identity/role-based-access-control/custom-overview
- Azure AI Services PII Redaction: https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to-call
- Confidential Inferencing Whisper Model: https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/azure-ai-confidential-inferencing-preview/ba-p/4248181
- Content Safety: https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview
- Prompt Shields: https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/general-availability-of-prompt-shields-in-azure-ai-content/ba-p/4235560
- Groundedness Detection and Correction: https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/correction-capability-helps-revise-ungrounded-content-and/ba-p/4253281
- Content Filters: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cuser-prompt%2Cpython-new
- Trustworthy AI: https://blogs.microsoft.com/blog/2024/09/24/microsoft-trustworthy-ai-unlocking-human-potential-starts-with-trust/
- HAX Toolkit: https://www.microsoft.com/en-us/haxtoolkit/