function buildPersonalWebsite() {
  const developer = new Developer('Enes Arıkan');
  const skills = ['React', 'TypeScript', 'Next.js', 'TailwindCSS'];
  
  developer.setExperience([
    { role: 'QA Engineer', company: 'Insider', years: 2 },
    { role: 'Software Tester', company: 'Various', years: 3 }
  ]);
  
  const projects = developer.createProjects([
    'E-commerce Platform',
    'Task Management App', 
    'Weather Dashboard',
    'Portfolio Website'
  ]);
  
  return {
    portfolio: developer.showcase(projects),
    blog: developer.shareKnowledge(),
    contact: developer.getContactInfo(),
    playground: developer.createInteractiveGames()
  };
}

class CareerJourney {
  constructor() {
    this.levels = [];
    this.currentLevel = 0;
    this.experience = 0;
  }
  
  addExperience(role, company, duration) {
    this.levels.push({
      title: role,
      company: company,
      duration: duration,
      skills: this.getSkillsForRole(role)
    });
    this.levelUp();
  }
  
  levelUp() {
    this.currentLevel++;
    this.experience += 100;
    console.log(`Level up! Now at level ${this.currentLevel}`);
  }
  
  getSkillsForRole(role) {
    const skillMap = {
      'QA Engineer': ['Testing', 'Automation', 'Bug Tracking'],
      'Frontend Developer': ['React', 'JavaScript', 'CSS'],
      'Full Stack Developer': ['Node.js', 'Databases', 'APIs']
    };
    return skillMap[role] || [];
  }
}

// Initialize the journey
const career = new CareerJourney();
career.addExperience('QA Engineer', 'Insider', '2 years');

// Bug hunting mini-game logic
function createBugHunt() {
  const bugs = [
    { type: 'NullPointerException', severity: 'high' },
    { type: 'RaceCondition', severity: 'critical' },
    { type: 'MemoryLeak', severity: 'medium' },
    { type: 'InfiniteLoop', severity: 'high' }
  ];
  
  return {
    findBugs: () => bugs.filter(bug => bug.severity === 'high'),
    fixBug: (bugId) => console.log(`Fixed bug: ${bugId}`),
    score: bugs.length * 10
  };
}

// Skill tree implementation
const skillTree = {
  frontend: {
    react: { level: 5, unlocked: true },
    typescript: { level: 4, unlocked: true },
    nextjs: { level: 4, unlocked: true }
  },
  testing: {
    automation: { level: 5, unlocked: true },
    manual: { level: 5, unlocked: true },
    performance: { level: 3, unlocked: true }
  },
  tools: {
    git: { level: 4, unlocked: true },
    docker: { level: 2, unlocked: false },
    kubernetes: { level: 1, unlocked: false }
  }
};

export default buildPersonalWebsite;
Back to Blog
Developer workspace with laptop and code
November 22, 2024·AI

How I Actually Use AI Tools in My Daily Workflow

Not a listicle of 50 tools. Just an honest breakdown of which AI tools genuinely changed how I work — and which ones I quietly stopped using.

AIProductivityDeveloper ToolsWorkflow

Every few weeks someone publishes a list of "100 AI tools that will change your workflow." I've tried a lot of them. Most don't stick. Here's what actually stayed in my day-to-day after months of real use — and what I quietly uninstalled.

What I Use Every Day

Claude (Anthropic): My primary writing and thinking partner. I use it for drafting bug reports, writing test case descriptions, summarizing long spec documents, and thinking through test strategies for complex features. The reason it stuck over ChatGPT: it's better at following nuanced instructions and more honest about uncertainty. It also produces less filler.

GitHub Copilot: Inside VS Code for scripting — Python test helpers, Appium scripts, data processing. The tab-completion for repetitive code patterns saves real time. I don't let it write logic I don't understand; I let it write boilerplate I'd otherwise type mechanically.

Cursor: When I need to work on a larger codebase rather than a single script, Cursor's codebase-aware features are noticeably better than Copilot. The ability to ask "why does this function do X" about code I didn't write is genuinely useful for QA work.

What I Use Several Times a Week

Perplexity: For research questions where I want citations alongside answers. When I'm looking up testing frameworks, Firebase configuration options, or industry practices, Perplexity surfaces sources I can verify rather than just asserting things. I trust it more than a pure LLM for factual lookup.

Midjourney: For app icon concepting and UI mood boards for Dainty Apps Lab projects. I generate 20 variations of an icon direction in 10 minutes instead of spending an hour in Figma on a direction I might abandon anyway.

Whisper (local): Transcribing meeting recordings and user interview sessions. I run it locally so no audio leaves my device. The transcripts feed into Claude for summarization and action item extraction.

What I Tried and Stopped Using

Notion AI: The integration is convenient but the output quality for technical writing felt weaker than Claude. I preferred keeping my notes in Notion and drafting in Claude separately.

Automated test generation tools (Testim, Mabl): The promise is compelling. The reality for mobile apps: these tools are built for web and the mobile support feels bolted on. The time spent configuring and maintaining the AI-generated tests outweighed the time saved, at least for the scale of projects I was running.

AI email summarizers: I tried several that auto-summarize inbox threads. The summaries were technically accurate but stripped out the tone and nuance I often need to understand the actual situation. Faster to just read the email.

How I Think About Adopting New AI Tools

The question I ask before trying a new tool: "What specific task am I spending 30+ minutes a week on that this tool could reduce?" If there's no clear answer, I don't bother.

The other filter: "Does this tool change how I work, or does it add a step?" The best tools reduce steps. Tools that add a step — even a small one — almost always get dropped within a month, regardless of quality.

The Honest Productivity Assessment

AI tools have genuinely changed my output on specific tasks: writing first drafts, generating structured documentation, scripting repetitive code, and researching unfamiliar topics. For those tasks, I'd estimate 30–50% time reduction.

They haven't changed the tasks that require judgment, contextual knowledge, and direct experience. Testing a new feature still requires me to understand the product, think about what could go wrong, and make calls about severity and priority. No AI tool is doing that for me.

The skill multiplier effect is real — but only for the skills you already have. AI makes a good QA engineer faster; it doesn't make a weak one better.

I built Mindpoke — a Chrome extension for focus and mindfulness — partly as an experiment in using AI throughout the development process. Details on the projects page.