New Azure AI Studio capabilities let customers train and debug generative AI-powered apps by comparing different versions of them and monitor apps in production for usage and quality. It also integrates with Microsoft Purview to discover potential data risks in AI apps, impose encryption on sensitive data and govern AI app usage. Copilot Studio is also introducing extensions and connectors, allowing developers to customize AI-powered copilots with instructions, knowledge from databases and actions from plugins, and ground a copilot with organizational knowledge from a range of different sources.
Key takeaways:
- Microsoft announced updates to its platforms for building generative AI-powered apps and experiences: Azure AI Studio and Copilot Studio.
- Azure AI Studio, now generally available, will allow developers to build generative AI-powered apps using pay-as-you-go inference APIs and integrates with Microsoft Purview to prevent unauthorized access to data across apps and services.
- Copilot Studio is launching Copilot agents, AI bots that can independently orchestrate tasks tailored to specific roles and functions, learning from user feedback and asking for help when they encounter situations they don’t know how to handle.
- New to Copilot Studio are extensions and connectors, allowing developers to customize AI-powered copilots with instructions, knowledge from databases and actions from plugins, and ground a copilot with organizational knowledge from a range of different sources.