Pedro Alonso RSS

I gave the same product spec to Claude Opus and to Qwen3.8-27B-UD-Q4_K_M on a single RTX 4090.

I ran the open-weights MiniMax H3 (Hailuo 3.0) video+audio model on a single 24 GB RTX 4090 and turned six storybook illustrations into a 31-second film with sound.

I gave my kids' book agent proper logging in a morning — three plain files — and spent the afternoon fixing what the logs immediately caught: 73% of GPU time wasted, books in the wrong language, and two ways the model broke its own tool calls.

I built a BCC-to-CRM email intake pipeline and ran it entirely on a single RTX 4090: deterministic threading, dedup, and quote-stripping, with a local Qwen3.6-27B doing exactly one job — turning a cleaned thread into a schema-valid activity entry. 40 out…

Naming a living illustrator in a prompt is the lazy way to get a style — and it makes the model forge their signature.

I RL-tuned a 3B model on a single GPU to tie Claude Opus 4.8 on text-to-SQL, then went query by query to show why an equal score doesn't mean an equal model.

The enterprise-knowledge-search question is really build-vs-buy: pay for Glean, self-host the open-source Onyx, or build RAG on the Postgres you already run.

Multi-step LLM agents fail halfway, wait on slow tools, and pause for human approval — so they need durable execution.

The tempting move is to hand an LLM your customer data and ask which accounts are about to churn.

How I built and run Reframe, an AI product-photo app for Shopify merchants: the architecture decisions that let one person operate a GPU pipeline in production, how session recordings drove churn down, and what it took to make an AI system merchants trust.

Every CRM quietly fills up with the same person entered three different ways — and you pay for it in wasted marketing, wrong reports, and split histories.

Empty chairs are pure lost revenue, and 'just text everyone a reminder' is the advice every practice gets.

A semantic cache on pgvector deletes the LLM calls you're paying for twice — but only if you tune it.

Everyone answers questions over their data with vector search.

Everyone reaches for an AI vector database to build 'people also bought.'

A practical guide to proving your LLM feature actually works — tracing, offline evals, and online monitoring — with an honest tour of the mid-2026 tooling landscape: Langfuse, Opik, Phoenix, DeepEval, Ragas, promptfoo, and where Trigger.dev fits.

Site selection is two search problems wearing a trenchcoat — where (spatial) and what-kind (semantic).

What it actually looks like to stop typing invoices into your accounting system: what week one looks like, what it costs, what still needs a human, and what breaks.

I ran three real invoices — a 1906 hardware bill, the handwritten Fabergé invoice for two Imperial Easter eggs, and a photographed Persian receipt — through a frontier vision model.

Why generative image editing failed for product photos, and the multi-model architecture that actually works — covering GPU deployment, cold starts, and the Build vs.

A practical, architecture-level guide to building a customer-support copilot with retrieval-augmented generation on Postgres alone — pgvector, BM25, and row-level security — and why big context windows changed RAG's job rather than killing it.

I benchmarked MTP speculative decoding for Qwen3.6-27B in llama.cpp on one 24GB RTX 4090 — it nearly tripled generation speed, and helped even on cold generation.

How I use Claude Code on a headless RTX 4090 server with tmux, git worktrees, and Tailscale to ship code from my laptop, iPad, or phone.

Bring production-grade BM25 ranking into PostgreSQL with pg_textsearch.

Moving beyond implementation to engineering discipline.

How I built a dedicated RTX 4090 AI server running Pop!

Build a secure, scalable multi-tenant SaaS architecture with PostgreSQL's Row-Level Security (RLS), Prisma, and Next.js.

Build real-time search and live updates in your Next.js app using PostgreSQL's native LISTEN/NOTIFY, Prisma, and WebSockets.

Ditch API routes and build forms, mutations, and async operations with zero API endpoints using Next.js Server Actions - the modern way to handle server-side logic

A real-world case study on using GitHub Copilot to diagnose and solve a persistent logging issue on my live Dokku server.

With a dynamic graph in place, we now focus on making our agent robust, scalable, and ready for production.

In Part 1, we replaced a monolithic prompt with a stateful agent.

Learn how to migrate from a fragile, monolithic prompt to a maintainable, intelligent agent architecture using specialized tools, state management, and human-in-the-loop patterns with LangChain.

Technical deep dive into automating client acquisition with AI agents - complete code for lead generation, cold email personalization, and scaling your automation business

How developers can dominate the automation market by building AI agents they'd actually use - and turning them into profitable services

Learn how to implement Stripe Payment Links and Customer Portal in Next.js 15 for the easiest payment integration with self-service customer management

Learn how to implement real-time server-to-client updates using Server-Sent Events in Next.js - a simpler alternative to WebSockets for one-way data streaming

Build production-ready payment systems with Stripe and Next.js 15 using Server Actions - from one-time payments to subscriptions and credit systems

Learn how to implement WebSockets with Next.js using native WebSocket APIs instead of Socket.IO - better performance, zero dependencies, and full control

Learn how to use Redis lists, queues, and pub/sub patterns in Next.js for real-time features and background processing

Learn about Implementing Pre-paid Usage Billing with Next.js and Stripe

Learn about Dokku Migrations: Introducing the Open Source Dokku Migration Tool

Learn about Building Practical AI Agents: From Tools to Workflows

Learn about Extending LLM Capabilities with Custom Tools: Beyond the Knowledge Cutoff

Learn about Building a Self-Healing LLM JSON Processor with Zod and Ollama (Deepseek 8b)

Learn about Advanced Background Processing in Next.js Part 2

Learn about Background Processing in Next.js Part 1

Learn about RAG Systems Deep Dive Part 3: Advanced Features and Performance Optimization

Learn about RAG Systems Deep Dive Part 2: Practical Implementation with LangChain

Learn about Next.js APIs with tRPC: A Developer's Guide to End-to-End Type Safety