Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Microsoft

Best Practices for Always-On Agents to Support Critical Workloads

Microsoft via YouTube

Overview

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 essential best practices and tools for building highly available and scalable AI agents that can handle critical workloads in this 47-minute conference session from Microsoft Ignite 2025. Discover how to ensure continuous availability at scale as AI agents increasingly drive critical workflows from frontline operations to executive decision-making. Explore Power Platform's resilience capabilities through real-world examples including the Norway Azure outage case study, and examine business risks associated with outages while understanding the importance of maintaining continuous operations. Navigate through a practical Copilot Studio insurance agent environment demonstration, understand failover processes including one-minute delays and potential data loss scenarios, and learn about the critical responsibilities involved in executing failover procedures. Master safe and resilient deployment practices, implement effective monitoring and scaling principles with emphasis on observability and automation, and discover how to automate disaster recovery through APIs while maintaining essential human oversight. Practice running compliance drills and simulated production failover scenarios to ensure your agents remain operational during critical situations, presented by Microsoft's Shivani Pradhan at the intermediate level.

Syllabus

0:00 - Power Platform’s resilience during the Norway Azure outage
00:03:05 - Business risks of outages and importance of continuous operations
00:09:27 - Exploring the Copilot Studio insurance agent environment
00:12:11 - Explaining one-minute delay and data loss during failover
00:12:45 - Warning about responsibility before executing failover
00:26:47 - Introduction of safe and resilient deployment practices
00:30:56 - Monitoring and scaling principles emphasizing observability and automation
00:35:31 - Automation of SSDR via API and Importance of Human Oversight
00:38:19 - Running Compliance Drills and Simulated Production Failover

Taught by

Microsoft Ignite

Reviews

Start your review of Best Practices for Always-On Agents to Support Critical Workloads

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.