Skip to content
Available for work · 2 weeks

Engineering at the edge
of code & intelligence.

Al Amin Ahamed · 4+ years shipping Laravel platforms, WooCommerce extensions, WordPress plugins, and TypeScript systems. Now building with LLMs and agents — and writing about both.

PHP Laravel WordPress WooCommerce TypeScript Postgres AI · LLM Agents
4+ Years shipping
42+ Projects built
39+ Posts written
38+ Open source
/Now

"At work: Senior Software Engineer at Codexpert. Deep focus on EasyCommerce — AI-driven product management, multi-vendor marketplace features, and performance work. Shipped several extensions to the WordPress.org repo thi..."

More →

02 · Writing

Recent essays

All writing · RSS →
May 22, 2026
· 0 min read

How I Cut Edit Distance from 168 to 43 in a Legal Document RAG Pipeline

Three architectural changes that brought average edit distance from 168 to 43 in a legal document RAG pipeline — section-scoped chunking, section-scoped exemplar prompting, and switching from a general embedding model to a legal-domain one — with a CI eval suite that made the improvement trajectory visible and reproducible.

May 22, 2026
· 0 min read

Designing a ReAct-Style Codebase Research Agent with Tool Use

How codebase-research-agent uses a ReAct loop to orchestrate semantic search, AST navigation, symbol lookup, grep, and git blame as callable tools — the hybrid retrieval substrate it operates on, and why framing RAG as a tool rather than a pipeline changes the architecture fundamentally.

May 22, 2026
· 0 min read

Building a 12-Source Job Discovery Pipeline with RAG and pgvector

How JobPulse aggregates job listings across 12 sources in three tiers, embeds your resume into pgvector, and generates grounded cover letters via Claude — including the async adapter protocol, composite scoring model, and the three retrieval failure modes that shaped the final architecture.

May 14, 2026
· 0 min read

Scaling a Laravel MCP Tool Registry to 46 Tools

The May 12 post covered the MCP server architecture. This one goes inside the tool registry: class-per-tool structure, Sanctum ability scoping, JSON Schema validation before dispatch, tag-based auto-discovery, and the three things that broke when the registry hit 46 tools.

03 · AI playground

Ask my writing.

Ollama embeddings · Openai · pgvector. Cited answers, real code.

avg latency 3.1s · always cites sources

04 · Stack snapshot

What I reach for

Full stack →
Languages
PHP TypeScript Go Python Rust
Frameworks
Laravel WordPress React Inertia.js Livewire Alpine.js Tailwind CSS
Databases
PostgreSQL MySQL / MariaDB Redis SQLite Meilisearch
AI / ML
Claude (Anthropic) Voyage AI LangChain / LlamaIndex pgvector Ollama OpenAI API
DevOps
Docker GitHub Actions Caddy Hetzner Cloud Supervisor Linux / Ubuntu
Tools
PhpStorm WP-CLI Pest PHPStan Laravel Pint Vite Playwright TablePlus Figma