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: harness, harnesses
Why it matters: Headline 'model X is better' claims are often really harness comparisons, so understanding the harness is essential to evaluating any agent result.
For example, two teams using the same model but different harnesses — different tool definitions, parsers, and prompts — can get wildly different success rates on the same benchmark.
Heard on the show
“So the authors re-ran the exfiltration scenarios in real production agent harnesses.”Episode 001 — When AI Models Quietly Protect Each Other From Shutdown