Agents

the first step to building evals is often times figuring out what you want to eval (sounds simple, in practice it has a lot of nuance)

the first step to building evals is often times figuring out what you want to eval (sounds simple, in practice it has a lot of nuance) you can condense long horizon evals with agents into smaller subs

DGX agentx-post
agentsharrison-chase--x

the first step to building evals is often times figuring out what you want to eval (sounds simple, in practice it has a lot of nuance) you can condense long horizon evals with agents into smaller subsets that still let you test intended behavior. i'm currently evaluating an agent that runs for 30+ minutes, and analyzes thousands of traces at a time. here's my process: if you're evaluating whether X impacts Y age…

Source: Harrison Chase (X) | 2026-05-20

Loading related sources…