# @mspowerplatform on YouTube

- **Type:** Video
- **Original URL:** https://youtube.com/watch?v=2IjDV_D3Jb0
- **Gondola URL:** https://gondola.cc/posts/59226140-mspowerplatform-youtube
- **Thumbnail:** https://img.gondola.cc/tr:w-,h-,fo-auto/postThumbnails/0d25b042fa.jpg
- **Posted:** 2026-03-04T17:00:10.000+00:00
- **Account Owner:** Microsoft Power Platform (@mspowerplatform) — https://gondola.cc/mspowerplatform

## Caption

Learn how to implement enterprise‑grade AI safety and content moderation in Microsoft Copilot Studio to protect your agents from harmful or sensitive inputs with Scott Durow. 

This mission walks you through configuring moderation levels, safety guardrails, and responsible AI disclosures to ensure fair, compliant, and professional agent behavior. Strengthen your multi‑agent systems with robust protections that uphold ethical AI principles across real‑world business scenarios.

👉🏻 Mission 06: AI Safety and Content Moderation - https://microsoft.github.io/agent-academy/operative/06-ai-safety/
👉🏻 Agent Academy | Operative - https://aka.ms/agent-academy-operative
👉🏻 Agent Academy | Recruit - https://aka.ms/agent-academy-recruit

TIMESTAMPS
00:00 Welcome!
00:15 Understanding AI Safety and Content Moderation
03:24 6.1 Adding AI Safety disclosure
04:12 6.2 Content moderation errors and custom messages
05:02 6.3 Adding custom error handling
06:27 6.4 Generative Answers content moderation level and prompt modification
07:48 6.5 Agent instructions control scope and responses
08: 19 6.6 Testing instruction-based blocking
08:31 6.7 and 6.8 Protection status, monitoring security threats
09:00 Wrap up

#copilotstudio #powerplatform #powerplatformadvocates

## Stats

- **Views:** 331
- **Likes:** 8
- **Shares:** 0
- **Comments:** 0

## Tags

powerplatformadvocates, copilotstudio, powerplatform

---
Copyright (c) Gondola