Zt Z.

Key Skills

Software

Other

Top Subject Matter

AI Response Evaluation and Chinese Language Quality

AI Prompt Engineering and Role Consistency Testing

Technical Research and Information Verification

Top Data Types

Text

Image

Top Task Types

Prompt + Response Writing (SFT)

Evaluation/Rating

Freelancer Overview

Long-term AI tool user since 2022, including ChatGPT, Gemini Advanced, Claude, Doubao, and Tongyi Qianwen. Hands-on experience includes AI response evaluation, basic prompt refinement, and local AI workflows. Practical experience with AI role/personality prompt testing and interaction style adjustment. Experienced in comparing AI outputs, fact-checking, and evaluating clarity, logic, and instruction-following in Chinese language outputs.

Labeling Experience

Basic AI Role Prompt Testing & Interaction Style Practice

OtherTextPrompt + Response Writing (SFT)

Engaged in creating, adjusting, and testing AI role/personality prompts within local and online AI chat environments. Focused on observing how prompt changes impacted dialogue quality, tone, role consistency, and context understanding. Gained practical experience with long-term AI tool usage including ChatGPT, Gemini Advanced, Claude, Doubao, and Tongyi Qianwen. Regularly compared AI outputs, identified common errors, and performed basic prompt refinement to improve response clarity, logic, and instruction-following in Chinese.

2024 - Present

Long-Term AI Tool Usage & Response Evaluation

OtherTextPrompt + Response Writing (SFT)

This experience involved comparing and evaluating text responses from multiple AI language models to determine accuracy, logic, and Chinese language suitability. Responsible for identifying errors, logical inconsistencies, instruction-following gaps, and conducting structured prompt refinement. Consistently practiced evaluation and troubleshooting using ChatGPT, Gemini Advanced, Claude, Doubao, Tongyi Qianwen, Kimi, and similar AI tools. • Performed accuracy and clarity checks on AI-generated text outputs. • Practiced prompt refinement to improve AI response quality. • Evaluated models’ output in both general and technical contexts. • Documented findings and model issues for personal learning.

2022 - Present

Education

Work History