Prompting
A technique where you write the start of the model's reply as the final assistant message, and the model continues from that text.
A technique where you write the start of the model's reply as the final assistant message, and the model continues from that text. It was commonly used to force a format, such as starting with an opening brace to get JSON or with "The answer is (" to get a single letter. Anthropic's docs state prefill is not supported on Claude 4.6 and later models, which return a 400 error, and recommend structured outputs or system prompt instructions instead.
Primary source: platform.claude.com
Example
It was commonly used to force a format, such as starting with an opening brace to get JSON or with "The answer is (" to get a single letter.
Hands-on guides, comparisons, and tutorials that cover Prompting.
FAQ
A technique where you write the start of the model's reply as the final assistant message, and the model continues from that text.
Assistant Prefill sits in the Prompting part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Developers Digest publishes tutorials and videos that cover Prompting topics including Assistant Prefill. Check the blog and YouTube channel for hands-on walkthroughs.
Related
A model trained to give a response a single score that predicts how much a human would prefer it.
The core cycle that powers AI agents: observe the current state, think about what to do next, act by calling a tool or generating output, then repeat.
A jailbreak is a prompt written to get a model to produce output its safety training is meant to refuse.

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.