This document describes how to use the Vertex AI prompt optimizer to automatically optimize prompt performance by improving the system instructions for a set of prompts.
The Vertex AI prompt optimizer can help you improve your prompts quickly at scale, without manually rewriting system instructions or individual prompts. This is especially useful when you want to use system instructions and prompts that were written for one model with a different model.
We offer two approaches for optimizing prompts:
- The zero-shot
optimizer
is a real-time low-latency optimizer that improves a single prompt or system
instruction template. It is fast and requires no additional setup besides
providing your original prompt or system instruction.
The zero-shot optimizer is model-independent and can improve prompts for any
Google model. Also, it provides a
gemini_nanomode to specifically optimize prompts for on-device models, such as Gemini Nano and Gemma 3n E4B . - The data-driven optimizer is a batch task-level iterative optimizer that improves prompts by evaluating the model's response to sample labeled prompts against specified evaluation metrics for your selected target model. It's for more advanced optimization that lets you configure the optimization parameters and provide a few labeled samples. Also, the data-driven optimizer supports optimization for generally-available Gemini models and supports custom models deployed locally or from the Vertex AI Model Garden.
These methods are available to users through the user interface (UI) or the Vertex AI SDK.
What's next
-
Learn about zero-shot optimizer
-
Learn about data-driven optimizer
