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.
More from coding & agent
- A research-agent ranking of 8 stock-data MCP servers puts Equibles first — DanielAPO · 2026-07-28
- Study of 100,000 developers finds AI coding gains shrink to about 30% at release stage — amcafee · 2026-07-28
- Building Self-Learning Pipelines and Multi-Turn Evals for Counselling Agents — Technical-Sort-8643 · 2026-07-28
- A new guide says most codebases are not ready for cloud coding agents — vinvan · 2026-07-28
- Meme asks whether to write code now or wait for a model that one-shots it — Darpinian · 2026-07-28
- UWaterloo open-sources Interactive Training 2 for auditable live model training — UWaterloo · 2026-07-28