Evaluator-Optimizer
Evaluator-optimizer is a workflow loop in which one model call generates a response and another evaluates it against criteria and provides feedback, repeating until the output passes.
Description
It works best when evaluation criteria are clear and when feedback demonstrably improves the output, as in literary translation or iterative search.
Sources
- Anthropic (2024). Building effective agents.
Cite this entry
Protologue. (2026). Evaluator-Optimizer. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0069). https://protologue.com/t/evaluator-optimizer/
BibTeX
@misc{protologue_evaluator_optimizer,
title = {Evaluator-Optimizer},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0069},
url = {https://protologue.com/t/evaluator-optimizer/}
}