AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → performance is increasingly bottlenecked by the agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition →, not the model: mismatches between intended and executed edits cost benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → points. Closing that gap alone reached state of the art on SWE-Verified and Terminal-Bench2 without task tuning.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
articleSix Agent Harness Capabilities for Higher Model PerformanceMichelle Horton
articleBeyond the Model: Demystifying Harness Effects in Software Engineering AgentsHaichuan Hu, Quanjun Zhang, Shengcheng Yu, Zhifei Chen, Tianyu Luo, Chunrong Fang, Zhenyu Chen, Liang Xiao
postThe Harness Is Everything: What Cursor, Claude Code, and Perplexity Actually BuiltRohit