Introduction
Unit 1 of 8 · Module 6: Implement a responsible generative AI solution in Microsoft Foundry
Read this lesson
Power and risk
Welcome to Module 6. Generative AI ranks among the biggest leaps technology has ever made. Developers can build on models that learned from vast amounts of internet data, and those models write new content that can be indistinguishable from something a person made. But anything that powerful can also do harm, the way a car that gets you anywhere also needs brakes, seatbelts, and rules of the road. So everyone who builds generative AI, from data scientists to developers, needs a responsible approach: one that finds the risks, measures them, and mitigates them.
The guidelines
This module follows a set of guidelines for responsible generative AI, written by experts at Microsoft. They extend Microsoft's Responsible AI standard to cover the risks that are specific to generative models. You'll plan a responsible solution in four stages: map the potential harms, measure them, mitigate them, and manage the solution once it's running. Then you'll put guardrails in place yourself, in Microsoft Foundry.
Facts from Microsoft's documentation: Overview of Responsible AI practices for Azure OpenAI in Foundry Models (CC BY 4.0), rewritten in Loop's own words and examples. Narration, animation, and quiz by Loop. Microsoft, Azure, and Microsoft Foundry are trademarks of Microsoft. Loop is independent and not affiliated with or endorsed by Microsoft.