AI Tech Suite

Prompt Picker

Click to visit website

About

Prompt Picker helps enhance your generative AI application by finding the most effective system prompts using a few example user interactions. This tool enables you to run experiments and evaluate multiple prompts simultaneously, leading to faster iterations and better user experiences. It aims to craft better user interactions, reduce costs per query by minimizing tokens consumed, and obtain more helpful chat responses. Users can configure their experiments by defining the setup, assessing generations through a blind comparison, and obtaining a ranking of the system prompts. Currently, Prompt Picker supports GPT-3.5-turbo and plans to introduce GPT-4 soon. It's currently free to use with a paid tier expected to come shortly.

Features

• run experiments to optimize prompts

• double blind experimental setup for assessment

• improve chat response quality

• reduce costs per query

• craft better user experiences

• evaluate multiple prompts in parallel

FAQs

What language models can I use?

Currently, only GPT-3.5-turbo is supported, but GPT-4 will be coming soon!

How much does it cost?

Prompt Picker is currently free to use, but we will be introducing a paid tier with more features soon.

How do you rank the candidate system prompts?

Based on pairwise comparisons provided by the user, Prompt Picker uses the ELO rating system to rank the candidate system prompts or custom instructions.