Ardhito K.

Key Skills

Software

Other

Top Subject Matter

LLM response evaluation and prompt evaluation for AI training

Indonesian-English bilingual content review and localization quality

AI-assisted workflow creation with instruction checking and validation

Top Data Types

Text

Image

Document

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

Prompt Evaluation & AI Response Comparison. Brings 2+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include ChatGPT Plus, Claude Code, and Gemini. Education includes N/A, Cheng Shiu University (2024). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Translation.

Labeling Experience

Indonesian-English Content Review

Text

Review Indonesian-English short-form and storytelling content to evaluate hook quality, structure, engagement patterns, and overall content quality signals. Categorize and save content samples for structured analysis to support ongoing bilingual review and localization QA. Track shifts between low-quality viral content and emerging educational trends to inform labeling criteria and content moderation decisions. • Hook-quality and structure evaluation for Indonesian short-form media • Engagement-pattern assessment and content trend tracking • Bilingual Indonesian-English review and localization QA • Categorization and storage of samples for analysis

2024 - Present

AI-Assisted Personal Projects

TextPrompt + Response Writing (SFT)

Support AI-assisted workflows through prompt-and-output review for personal productivity and automation experiments that require structured instruction checking. Use AI to help with logic review, configuration, safety checks, and workflow automation planning for downstream content or dataset workflows. Maintain consistent quality by applying human verification steps before relying on AI-generated guidance. • AI-assisted workflow automation planning using Notion and Google Calendar • Logic review and safety checks for an RSI-based MT5 automation experiment • Configuration verification for AI-assisted research/lead identification • Prompt iteration and human validation for reliable automation outputs

2022 - Present

Prompt Evaluation & AI Response Comparison

Text

Conduct prompt evaluation by comparing outputs across multiple LLMs to assess clarity, accuracy, tone, and instruction-following. Apply rubric-based multi-criteria testing to understand how framing and language affect model behavior for real tasks such as translation and content review. Perform human-in-the-loop evaluation and quality assurance on AI responses to flag edge cases and improve downstream annotation workflows. • Side-by-side comparisons of ChatGPT, Claude, Gemini, and DeepSeek • Prompt engineering and role-based prompt design for evaluation • Accuracy/clarity/tone checks and instruction-following verification • Edge-case flagging and iterative application to active review tasks

2022 - Present

Education

Work History