Agent quality now depends more on context and harness design than on prompting

verrsane · x · 2026-07-28

Andrej Karpathy’s point is that agent quality is no longer mostly about prompting.

The article argues that the real bottleneck is the harness around the model: context management, specs, tools, and workflows. Those surrounding systems determine whether an agent can actually reason over long tasks, use tools reliably, and stay on track.

In other words, building agents has shifted from writing better prompts to engineering the runtime that feeds, constrains, and evaluates the model.

Original post →

More from coding & agent

coding & agent channel →