Content by Sanjeev Jagtap, Lee Stott, Marie-Louise Onga Nana (1)

How to run evals for the model router

Sanjeev Jagtap, Lee Stott, and Marie-Louise Onga Nana walk through an open-source evaluation pipeline for Azure AI Foundry’s model router, showing how to measure quality, cost, and latency, inspect model-selection distribution, and optionally submit results back into Foundry’s enterprise evaluation tooling.
News

End of content

Rejoining the server...

Rejoin failed... trying again in seconds.

Failed to rejoin.
Please retry or reload the page.

The session has been paused by the server.

Failed to resume the session.
Please reload the page.