# Evaluator-Optimizer

> A workflow where one model produces work and another model evaluates it, creating an improvement loop.

- Category: Agents & Autonomy
- Stage: Established
- Also called: Critic loop, Review-and-revise loop
- Canonical: https://www.joelcsaji.com/ai-dictionary/evaluator-optimizer

## Plain English

One AI writes; another AI reviews; the first AI revises.

## Example

A drafting agent writes a policy summary, then an evaluator checks completeness and flags unsupported claims.

## Why it matters

It can raise quality when the success criteria are clear enough to evaluate repeatedly.

## Related

- [Evals](https://www.joelcsaji.com/ai-dictionary/evals)
- [Self-Reflection](https://www.joelcsaji.com/ai-dictionary/self-reflection)
- [Judge Model](https://www.joelcsaji.com/ai-dictionary/judge-model)

## Sources

- [Anthropic: Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents)