Skip to content
View h2so4nackl-code's full-sized avatar
  • Joined Jul 5, 2026

Block or report h2so4nackl-code

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
h2so4nackl-code/README.md

Hi, I'm h2so4nackl-code 👋

AI Evaluation • Prompt Engineering • Technical QA • AI-Assisted Software Testing

I'm an AI enthusiast and independent technical tester with 1+ year of daily hands-on experience using generative AI for prompt engineering, technical problem-solving, workflow evaluation, and software testing.

My focus is practical AI response evaluation, technical QA, AI-assisted software testing, technical documentation, and CLI workflow testing.

Featured Projects

A portfolio of 40 complete, fictional AI response evaluations demonstrating evidence-based review and practical scoring judgment.

  • Worked evaluations across eight task categories
  • Anchored 1–5 scoring with evidence, strengths, weaknesses, and suggested improvements
  • Controlled response comparisons, reusable scorecards, prompts, and templates

A model-agnostic handbook for practical AI response evaluation and quality review.

  • Evidence-based scoring with anchored 1–5 rubrics
  • Reviewer calibration, disagreement resolution, evaluation bias awareness, and multilingual considerations
  • Reusable checklists, decision trees, worked examples, case studies, and templates

A practical, model-agnostic knowledge base for structured prompt design across AI evaluation, technical QA, troubleshooting, software testing, and documentation.

  • Prompt design principles and repeatable workflows
  • Reusable QA, troubleshooting, and documentation templates
  • Fictional, anonymized case studies demonstrating evidence-based analysis

What I Work With

  • Prompt engineering for practical testing and troubleshooting tasks
  • AI response evaluation for clarity, accuracy, consistency, and usefulness
  • AI-assisted software testing and technical troubleshooting
  • Bug reproduction, reporting, and workflow validation
  • Technical documentation and clear test feedback
  • Windows, Android, PowerShell, WSL, GitHub, and CLI workflows

Current Focus

  • Evaluating AI-assisted workflows and improving prompt quality
  • Building repeatable test cases for technical and CLI-based workflows
  • Independently testing DEX.DO on Shellnet, including end-to-end BUY/SELL flows
  • Producing clear bug reports and collaborating with developers through public GitHub issue discussions

I enjoy learning new AI tools, comparing their capabilities, and documenting practical workflows that improve productivity, software quality, and AI-assisted problem solving.

Currently Learning

  • AI evaluation methodologies
  • Prompt optimization techniques
  • Technical QA workflows
  • CLI-based testing
  • Git & GitHub best practices
  • AI-assisted automation

Goals

  • Build high-quality AI evaluation projects
  • Improve prompt engineering techniques
  • Expand my public technical portfolio
  • Contribute to AI testing and documentation

Core Skills

  • Prompt Engineering
  • AI Evaluation
  • Technical QA
  • Bug Reproduction
  • Workflow Testing
  • Technical Troubleshooting
  • Technical Documentation
  • GitHub Collaboration
  • CLI Workflows

Selected Experience

  • 1+ year of daily hands-on use of generative AI tools
  • Independent DEX.DO testing on Shellnet, including CLI testing and end-to-end BUY/SELL workflow validation
  • Reproduction and reporting of technical issues with clear steps and observations
  • Public technical communication with developers through GitHub issue discussions

Tools and Technologies

AI Models

  • ChatGPT
  • Claude
  • Claude Code
  • Codex
  • Grok
  • Perplexity
  • Gemini

Development & Testing

  • Git
  • GitHub
  • PowerShell
  • WSL
  • CLI

Operating Systems

  • Windows
  • Android

Interests

  • Artificial Intelligence
  • AI Evaluation
  • Technical QA
  • Prompt Engineering
  • Workflow Automation
  • Blockchain Applications
  • Emerging AI Technologies

Languages

  • Romanian: Native
  • English: Intermediate
  • German: Intermediate

Contact

Feel free to explore my repositories or connect with me here on GitHub.

This portfolio will continue to grow as I document new AI workflows, testing projects, and technical learning experiences.

Pinned Loading

  1. ai-evaluation-portfolio ai-evaluation-portfolio Public

    Practical AI response evaluation portfolio with evidence-based scoring, worked reviews, and controlled response comparisons

  2. ai-prompt-engineering ai-prompt-engineering Public

    Practical, model-agnostic prompt engineering knowledge base for AI evaluation, technical QA, troubleshooting, and software testing

  3. ai-response-evaluation-lab ai-response-evaluation-lab Public

    Model-agnostic AI response evaluation handbook with evidence-based rubrics, calibration guides, case studies, and reusable templates