---
id: "quote-harness-definition"
type: "quote"
source_timestamps: ["§ Can Someone Please Define a \"Harness\"?"]
tags: ["definitions"]
related: ["concept-agent-harness", "claim-agent-equation"]
speaker: "Vivek Trivedy"
speakers: ["Vivek Trivedy"]
quote: "If you're not the model, you're the harness."
---
# If you're not the model, you're the harness.

## Quote

> **“If you're not the model, you're the harness.”** — [[entity-vivek-trivedy|Vivek Trivedy]]

## Context

The author's succinct heuristic for dividing the architecture of an AI agent system. It collapses [[claim-agent-equation|the Agent = Model + Harness equation]] into a single decision rule: when looking at any component of an agentic system, classify it as either *the model* (a forward pass over weights) or *the harness* (everything else). There is no third category.

## Why It Matters

This framing has been adopted widely (Martin Fowler, Anthropic, Parallel AI, arXiv surveys). It clarifies design discussions: arguments about “agent improvements” can immediately be sorted into model-side improvements vs. [[concept-agent-harness|harness-side]] improvements, which have entirely different teams, tools, and time horizons.