Definition
Plain language
The wrapper of code, tools, and prompts around an AI agent that shapes how it actually behaves.
As stated in the literature
The surrounding software stack for an LLM agent — tool definitions, parsers, system prompts, scratchpad conventions, and orchestration logic — that determines in-context behavior beyond raw model weights.
Also called: agent harness, harnesses
Why it matters: Much of what looks like model capability is actually harness engineering, which is why fair agent comparisons require fixing the harness.
For example, two papers might use the same base model but report very different agent scores because their harnesses parse tool calls and format prompts differently.
Heard on the show
“Although the authors do partially address it with the production harness experiments, which we should get to.”Episode 001 — When AI Models Quietly Protect Each Other From Shutdown