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.
Stop Treating Your Users Like Strangers: Identity Resolution for RAG
Move beyond generic RAG. Discover how to use identity resolution and RudderStack Profiles to build a behavioral context layer for truly personalized AI assistants.
Beyond the Pixel: Building a High-Signal Pipeline with RudderStack Server-Side Event Tracking
Move beyond fragile client-side pixels. This guide covers implementing RudderStack server-side tracking and transformations for real-time data enrichment and identity stitching.
Stop Building Blind Agents: A RudderStack Real-Time Context Pipeline with Redis
Learn to use RudderStack Transformations and Redis to create a real-time behavioral context layer, providing LLM agents with low-latency session awareness and stateful signals.
The Model is a Commodity: Why Your 2026 Moat is Actually Just Great Data Engineering
LLMs are commodities by 2026. This article explores why engineering leaders must prioritize data reliability and "Context Hydraulics" over model selection to build a defensible AI moat.
The Agentic Pivot: Leading Your Team from Retrieval to Autonomous Execution
Stop treating AI as a librarian and start building executors. Explore the architectural shift from RAG retrieval to stateful agentic workflows using Laravel, Kafka, and tool meshes.
Gemini 4 Argon: Google Finally Breaks the Output Token Ceiling
Gemini 4 Argon shatters output limits with a 1M token ceiling. We analyze the architectural shifts, async patterns, and pricing structures required for high-scale agentic workflows.
The Business Logic Ranker: Using Vespa.ai Tensors to Inject Profitability into RAG Results
Moving beyond similarity with Vespa.ai Tensor Ranking Expressions allows developers to weigh user intent against real-time signals like profit margins and inventory status in RAG systems.
The Governance Debt: Why Your 2026 AI Roadmap Needs a Behavioral Guardrail
Move beyond simple prompt engineering to a risk-weighted governance framework. Learn to manage behavioral drift as agents gain native computer-use capabilities in production environments.
The Fine-Tuning Trap: Why Your 2026 Roadmap Should Favor RAG Over Custom Models
Avoid weight rot by prioritizing RAG over fine-tuning. This guide explores the AI build vs buy decision matrix for 2026, focusing on context orchestration and architectural agility.