Press Space to continue
Agent improvement comes from system design, not bigger models
Press Space to continue
I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provided - how you recover from failure - what gets measured afterward That’s the loop we’re building around deepagents (the orchestration logic) + LangSmith (how you measure)
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.