Experiments

Exploring AI integration, performance optimization, and software architecture through tutorials and experiments

Categories

Tags

agentic-engineeringaiai-agentsai-codingai-convergenceai-developmentautomationclaudeclaude-codeclideveloper-toolsdevelopment-workflowgeminillmlspmcpmcpxmethodologynextjsportfolioragrtkrustserenasoftware-architecturesparcspec-driven-developmentspecificationstddtessltoken-efficiencytree-sittertypescriptweb-dev
aiFeatured

The AI Convergence: Why Every Coding Tool Lands on the Same Two Defaults

March 23, 2026 · 17 min read

AI coding tools are converging on two outputs -- React + TypeScript when a build pipeline exists, plain HTML when it doesn't. The forces behind this are mechanical, self-reinforcing, and quietly killing language innovation.

ai-convergencetypescriptai-development
aiFeatured

MCP Is a Crutch: Why CLI Tools Are the Future of AI Agent Tooling

March 9, 2026 · 10 min read

How MCPX transforms MCP servers into zero-overhead CLI tools, and why the OpenClaw CEO is right that CLI is the natural interface for agentic systems.

mcpxmcpcli
ai

SPARC: The Methodology That Turns Vibe Coding Into Actual Engineering

March 9, 2026 · 11 min read

Why structured AI-assisted development with SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) produces 4x better results than raw prompting, and how to adopt it today.

sparcai-developmentmethodology
ai

Spec-Driven Development: Why Writing Specs Before Code Is the Next Paradigm Shift

March 9, 2026 · 11 min read

How Tessl pioneered spec-driven development to eliminate AI hallucinations, reduce rework, and make specifications — not code — the source of truth.

spec-driven-developmenttesslai-coding
ai

RTK: The Rust Binary That Slashed My Claude Code Token Usage by 70%

March 1, 2026 · 15 min read

How a single Rust CLI proxy compresses command output before it hits the LLM context window, and why pairing RTK with Serena MCP creates the most token-efficient AI coding setup I have ever used.

rtkclaude-codetoken-efficiency
ai

From Vibe Coding to Symbolic Reasoning: How Serena MCP Gives AI Agents X-Ray Vision

February 11, 2026 · 17 min read

Why vector search fails at code understanding and how Serena MCP uses the Language Server Protocol to give AI agents the same precise, deterministic vision developers have in their IDEs.

serenamcplsp
ai

Surgical Code Editing: The 10x Token Efficiency Pattern

February 9, 2026 · 20 min read

Why full-file rewrites cost 10x more tokens and how symbolic operations with AST-based editing transform AI agent workflows from brute-force to surgical precision.

claudeai-agentstoken-efficiency
ai

Building a Complete Portfolio Using Only AI: Zero Human Code

February 8, 2026 · 23 min read

How I leveraged Claude Code, Gemini, and AI-driven development to build a production-ready portfolio from scratch with zero human code modifications—only planning

aiclaudegemini