.NET AI Community Standup: Routing & Failover for Microsoft.Extensions.AI
Bruno Capuano and Joshua Yue discuss routing and failover patterns for Microsoft.Extensions.AI, explaining the design decisions behind a resiliency approach Joshua built at Microsoft and how .NET teams can apply it to keep AI features running when a model or provider becomes unavailable.
Overview
The session focuses on making .NET AI applications more resilient by adding routing and failover behavior around Microsoft.Extensions.AI so an app can continue operating when an LLM model endpoint or provider goes down.
Key themes covered:
- How routing can direct requests to different models/providers based on availability or policy.
- How failover can automatically switch to a fallback provider when the primary provider is unavailable.
- The design decisions behind the routing/failover implementation Joshua built during his Microsoft internship.
- Practical guidance on applying these patterns in real .NET AI apps.
Links
- Microsoft Learn collection: https://learn.microsoft.com/en-us/collections/2gqmsgtg431pgk?source=docs
Speakers
- Bruno Capuano: https://www.linkedin.com/in/elbruno
- Joshua Yue: https://www.linkedin.com/in/joshuajyue/