Guardrails & Safety Nets (Evals) for the New Landscape

Discover how teams are building evaluation systems, feedback loops, and safety mechanisms to make AI-powered systems reliable and trustworthy.

From this track

Session

How Airbnb Guardrailed Its AI Customer Support Agent

When Airbnb launched its AI customer support assistant, the feature made the news — the guardrails built to make it safe to ship did not. Yet an AI agent that talks to millions of customers, remembers a conversation across turns, and can trigger account actions is a

Session

AI Inside and Out: New Guardrails for When AI Is Both Your Tool and Your User

AI is changing our systems from two directions simultaneously - and most teams are only watching one.

Speaker image - Daria Barteneva

Daria Barteneva

Principal Site Reliability Engineer in Observability Engineering @Microsoft Azure

Speaker image - Tim Ren

Tim Ren

Partner Group Engineering Manager @Microsoft

Date

Monday Nov 16 / 10:35AM PST

Share

Share Share

Track Host

Tanya Reilly

Principal Engineer @Datadog, Author of "The Staff Engineer's Path", Likes Going Places on Trains

Tanya Reilly is a principal engineer at Datadog, and was previously a senior principal engineer at Squarepace and a staff engineer at Google. A former systems administrator and SRE, she's fascinated by complex systems and how software runs in the messy real world.

She's the author of the Staff Engineer's Path, a book about how to survive and thrive as a very senior individual contributor.

She's originally from Ireland, but spent more than a decade in Brooklyn, and currently lives in Albuquerque, New Mexico. She likes hiking with her kid, photographing birds, and going places on trains. Her answer to the official New Mexico state question is "green".

Read more
Find Tanya Reilly at: