---
id: "quote-cannot-automate-score"
type: "quote"
source_timestamps: ["00:21:50", "00:21:55"]
tags: ["evaluation", "automation"]
related: ["claim-cannot-automate-unmeasurable", "prereq-evaluation-infrastructure", "action-build-eval-infrastructure"]
speaker: "Nate B. Jones"
speakers: ["Nate B. Jones"]
quote: "You cannot automate what you cannot score."
sources: ["s04-karpathy-agent-700"]
sourceVaultSlug: "s04-karpathy-agent-700"
originDay: 4
---
# You cannot automate what you cannot score

## Quote
> "You cannot automate what you cannot score."

— [[entity-nate-b-jones|Nate B. Jones]]

## Context
A foundational rule for deploying autonomous agents: without a programmatic, objective metric, an optimization loop cannot function.

## Anchors
- Claim: [[claim-cannot-automate-unmeasurable]]
- Prerequisite: [[prereq-evaluation-infrastructure]]
- Action: [[action-build-eval-infrastructure]]

## Practical Reading
If operators take only one rule from the source, this is it. Building programmatic evaluation infrastructure is the gating prerequisite for autonomous improvement.