Improve your prompts in the developer console
Today, we're introducing the ability to improve prompts and manage examples directly in the Anthropic Console. These features make it easier to leverage prompt engineering best practices and build more reliable AI applications.
Prompt quality plays a significant role in how successful a model's responses are for a given task. However, prompting best practices take time to implement and often vary across model providers.
The prompt improver allows developers to take existing prompts and leverage Claude to automatically refine them using advanced prompt engineering techniques. This is ideal for adapting prompts that were originally written for other AI models, as well as for optimizing hand-written prompts.
Once the new prompt is generated, you can provide feedback for Claude about what is and isn’t working to further improve the prompt.
Our testing shows that the prompt improver increased accuracy by 30% for a multilabel classification test1 and brought word count adherence up to 100% for a summarization task.2
