Intel / video

Always-on agents run production without the on-call tax — Justin Smith, Resolve AI

Source: youtube.com
Author: AI Engineer
Date: Published Aug 7, 2026

Context

A deployment-monitoring can use the code changes in a release to decide what to watch. In Resolve AI's presentation, a simulated environment illustrates an agent identifying a release, examining its changes and selecting relevant performance measurements and error rates.

The proposed benefit is more specific monitoring than repeating the same checks for every deployment. A change affecting checkout, for example, prompts to checkout latency and connected services. The agent can continue checking when a problem might emerge later. This describes a contextual monitoring capability; the demonstration supplies no measurement of reduced incidents or eliminated on-call work.

Terms in this piece · Glossary

AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.

Key quotes

“really coding was never the the the big bottleneck, right?”
Justin Smith

“it's one thing to go check a dashboard. It's another thing to say that metric smells off.”
Justin Smith

“any change inside of your environment is an opportunity for something to go wrong”
Justin Smith

“this is for anybody that's had to be on call before, um you know, on call is a it's a nightmare, right?”
Justin Smith

“it would be great if you had a single engineer just focused on like watching all the things on every release, but that's really expensive”
Justin Smith

Read the source www.youtube.com