Prefill
Also called response prefilling, output priming, assistant prefill.
Prefill is the technique of writing the first part of the model's response yourself, so that the model continues from that text and is steered into a specific format or direction.
Description
Starting the assistant turn with an opening brace pushes the model toward JSON output, and starting with a heading or a character's name can enforce structure or persona. Support is model-specific and declining. Anthropic's documentation states that prefilling the final assistant turn is not supported on Claude 4.6 models and later, and recommends explicit instructions or structured outputs instead.
Sources
- Anthropic (2026). Prompting best practices.
Cite this entry
Protologue. (2026). Prefill. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0015). https://protologue.com/t/prefill/
BibTeX
@misc{protologue_prefill,
title = {Prefill},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0015},
url = {https://protologue.com/t/prefill/}
}