tech

AI, Code & E-commerce

Articles on AI automation, web development, Next.js, SEO, and scaling e-commerce businesses. 106 articles.

I write about the tools and systems I actually build with — from multi-agent AI pipelines and MCP servers to Next.js full-stack apps, Supabase backends, and SEO automation. Every article comes from a real project: shipping production code, scaling e-commerce stores, or wiring up AI agents that do useful work. If you're a developer, founder, or just curious about how modern web stacks fit together, you'll find practical walkthroughs, honest trade-offs, and working code examples here. Topics span AI and LLM integration, cloud infrastructure (Vercel, AWS, Docker), developer tooling, and the business side of building software products.

64 articles tagged AI

Qwen Code vs Kimi Code: The Free AI Coding Agent Wave Is Here
AIQwen CodeKimi Code+4
Read article

Qwen Code vs Kimi Code: The Free AI Coding Agent Wave Is Here

Qwen Code and Kimi Code turned July 2026 into an agent-tools month, not just a model month. Here is where each tool wins, where OmniRoute and OfficeCLI fit, and why I still keep premium models in reserve.

Uygar DuzgunU
Uygar DuzgunJul 25, 2026
10 min read
AI Reasoning Tokens: More Tokens, Better Results, More Power
AIOpenAIAnthropic+5
Read article

AI Reasoning Tokens: More Tokens, Better Results, More Power

OpenAI and Anthropic make the tradeoff visible: better AI answers often need more reasoning tokens, more inference compute, and more electricity.

Uygar DuzgunU
Uygar DuzgunJul 14, 2026
7 min read
Code Agents After 21.54 Billion Tokens: What’s Missing?
AICode AgentsMCP+3
Read article

Code Agents After 21.54 Billion Tokens: What’s Missing?

I ran 21.54 billion activity tokens through real code-agent work. The models improved, but the system still matters more.

Uygar DuzgunU
Uygar DuzgunJul 12, 2026
8 min read
Shoutout: Matthew Berman Makes AI Easier to Understand
AILearningYouTube+1
Read article

Shoutout: Matthew Berman Makes AI Easier to Understand

A short thanks to Matthew Berman for explaining AI clearly and making complex ideas easier to understand.

Uygar DuzgunU
Uygar DuzgunJul 8, 2026
1 min read
GLM-5.2 NVIDIA Free API: Benchmarks and Limits
AINVIDIAGLM-5.2+3
Read article

GLM-5.2 NVIDIA Free API: Benchmarks and Limits

GLM-5.2 is now on NVIDIA's free API. Here are the benchmark numbers, the 40 RPM limit, and why max tokens need practical testing.

Uygar DuzgunU
Uygar DuzgunJul 3, 2026
7 min read
Roboflow Supervision: Benchmarks for Apps
AIComputer VisionRoboflow+2
Read article

Roboflow Supervision: Benchmarks for Apps

Supervision is not another model. It is the tool layer that turns computer vision outputs into something apps can use.

Uygar DuzgunU
Uygar DuzgunJul 3, 2026
8 min read
24h with Claude Fable 5
AIClaude Fable 5Claude Code+7
Read article

24h with Claude Fable 5

I spent 24 hours with Claude Fable 5 across AI bridge reviews, MCP work, and a headless WordPress clone. This is where it felt different.

Uygar DuzgunU
Uygar DuzgunJul 2, 2026
8 min read
WordPress Is Dead as the Default Website Builder
WordPressEmDashCloudflare+6
Read article

WordPress Is Dead as the Default Website Builder

WordPress still dominates the web, but Cloudflare's EmDash and AI-assisted builds show why it is no longer the default choice for custom websites.

Uygar DuzgunU
Uygar DuzgunJun 30, 2026
9 min read
Claude Code /loop and /goal vs OpenAI Codex /goal
AIClaude CodeCodex+4
Read article

Claude Code /loop and /goal vs OpenAI Codex /goal

How I use Claude Code /loop, Claude /goal and OpenAI Codex /goal to turn AI coding agents into verifiable long-running workflows.

Uygar DuzgunU
Uygar DuzgunJun 25, 2026
11 min read
Best Free AI Coding Tools: The Stack I'd Use in 2026 After GPT-5.5
AIDev ToolsOpen Source+2
Read article

Best Free AI Coding Tools: The Stack I'd Use in 2026 After GPT-5.5

GPT-5.5 raised the bar, Claude Fable 5 vanished three days after launch, and Google pushed Gemini CLI users toward Antigravity. This is the $0 coding stack I would use now.

Uygar DuzgunU
Uygar DuzgunJun 21, 2026
10 min read
Hybrid AI Code Review: Claude Opus 4.8 + Codex in a Loop
AIClaude Opus 4.8Codex+6
Read article

Hybrid AI Code Review: Claude Opus 4.8 + Codex in a Loop

Two frontier models in a loop: Claude Opus 4.8 writes each fix, Codex reviews it through my AI bridge, and a real build votes. 39 production fixes, none by hand.

Uygar DuzgunU
Uygar DuzgunJun 20, 2026
7 min read
MCP Developer Workflows: The Real Control Layer
AIAutomationDev Tools+1
Read article

MCP Developer Workflows: The Real Control Layer

MCP developer workflows are the control layer for production agents: scoped tools, approval gates, source-backed context, and replayable actions.

Uygar DuzgunU
Uygar DuzgunJun 19, 2026
8 min read