Writing
The Blog
Engineering notes, build logs, and thoughts on creative development.
Building AI-Native Apps: Vector Search in Laravel 13 & PostgreSQL
This guide explores how Laravel 13 has revolutionized search by introducing native vector similarity methods. We cover everything from the basic whereVectorSimilarTo syntax to the advanced orchestration of embeddings using the new Laravel AI SDK, providing a clear path for architects to build intelligent, semantic search engines.
The Silent Search Killer: Using dbt Tests to Guard Your Vector Ingestion Pipeline
Stop silent search degradation by implementing dbt macros to validate vector dimensions, L2 norms, and semantic drift across your ingestion pipelines.
The Privacy Moat: Implementing Hard Multi-Tenancy in pgvector with PostgreSQL RLS
Secure your RAG architecture by moving from application-side metadata filtering to database-level isolation using pgvector multi-tenancy, PostgreSQL RLS, and HNSW optimization.
Livewire v4 + Reverb: Streaming Asynchronous AI Agent Responses Word-by-Word
An extensive technical layout tutorial constructing an interactive, token-streaming interface using Laravel 13. We walk through extracting real-time generative updates from the new first-party AI SDK, isolating heavy calculations via background workers, and feeding tokens straight to Livewire v4 components using Laravel Reverb WebSockets.
Hybrid Retrieval 2.0: Tuning HNSW Parameters for pgvector at Scale
Optimize pgvector HNSW parameters for million-row vector databases. This guide covers m, ef_construction, and memory management for production-grade RAG.
Hallucination-Proofing Your Agent: Building a RAG Evaluation Framework in PHP
Eliminate AI hallucinations by building a native RAG evaluation framework in Laravel 13 using Pest, LLM-as-a-judge, and quantitative metrics to verify agent faithfulness.
Model Context Protocol in Laravel: Building MCP Servers with the AI SDK
Standardize your AI integrations by building MCP servers in Laravel 13. Learn to map tools to resources and implement SSE transports for high-scale Kafka and vector data pipelines.
Architecting for the Bill: Building an LLM Rate Limiter and Cost Tracker in Laravel
Learn how to build a robust LLM cost management system in Laravel 13 using middleware to track tokens, manage multi-tenant budgets, and prevent runaway costs.
Event-Driven Ingestion: Scaling Search Pipelines with Kafka and dbt
An enterprise data architecture tutorial focused on building a high-throughput search ingestion pipeline. We demonstrate how to break up transactional database dependencies by using Apache Kafka for immutable event routing, coupled with dbt incremental models to manage near-real-time data transformations smoothly at scale.
Two-Stage Retrieval: Cross-Encoder Reranking with Laravel 13 AI SDK
An deep-dive architectural tutorial demonstrating how to combine first-stage vector recall via pgvector with second-phase precision sorting using the Laravel 13 AI SDK Reranking engine. It walks through the mechanics of Bi-Encoders vs. Cross-Encoders and provides a clean implementation roadmap using native collection macros.