Content by jonah andersson and danielle cass (1)

Jonah Andersson and Danielle Cass explore guardrails, evaluation, and human-in-the-loop patterns for safer AI agent workflows. This intermediate Microsoft Ignite 2026 session focuses on approaches that help agents remain useful and reliable while making their behavior easier to trust.
Videos

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.