Hello! One of the blog's co-authors here. Faster analysis and lower cost is the goal. We think that a Jev-driven pipeline can be a quick fast-path filter for a lot of alerts that are recurring or even false-positives.
We can also add a confidence output to this pipeline, so we invoke a heavier reasoning agent (like Sonnet) when something suspicious deserves a closer look.
We can also add a confidence output to this pipeline, so we invoke a heavier reasoning agent (like Sonnet) when something suspicious deserves a closer look.