Extracting structured data from messy text: what worked for me
I spent a good two weeks last quarter building an invoice extraction pipeline for our accounting...
Tutorials
Catching the failure is the easy part
The last post I wrote ended on a loose thread I have not been able to stop pulling at. Almost every...
I tried 5 ways to build a Q&A system over my docs — here's what worked
Last month, I needed a way to ask natural-language questions about a pile of internal documentation....
500 portadas distintas de un solo modelo de $0.04: arte de portada con IA, consistente con la marca, en un generador económico
La lección de cabecera: en un modelo económico, la calidad no la consigues escribiendo un mejor...
My morning BTC checklist uses three agents — here's what it actually said the day BTC bottomed
BTC Max Profit Engine is a 4-file Python pipeline that runs three specialized agents in parallel, weights their scores, and emails me one decision before breakfast. Here's the work...
I built a region-survivable system by directing an AI agent. An append-only decision log kept it coherent.
Most of Quorum's code was written by directing an AI coding agent. The discipline that turned that speed into a correct multi-region database application was an append-only archite...
hosted coding agents make observability a product feature
The laptop was never the interesting part of coding agents. It was just the first convenient runtime. Your laptop has the repository, the shell, the secret
The most underrated feature in a website AI assistant: saying "I don't know"
A lot of teams are bolting a chatbot onto their marketing site this year. Most of them optimize for...
Reputation You Can Mint for Free Is Not Reputation
Sybil resistance is not a scoring problem. It's a pricing problem. Every few months someone...
A Cognitive Benchmark for Code-RAG Retrieval: Part 2 — Why Model Rankings Depend on the Pipeline
How embedding models, chunking, retrieval modes, and query phrasing jointly determine Code-RAG quality.
The spec is in the wrong place
My day job is at a large tech company. Hundreds of engineering teams, and every one of them is...
@hazeljs/agent 1.0.1: Production Hardening for Real Deployments
We are shipping @hazeljs/agent 1.0.1 — a patch release focused on operational durability, resilience...
I built an AI code reviewer as a GitHub Action — here's what I learned
If you've spent time on software engineering teams, you know pull request reviews are the ultimate...
We burned 136 million tokens running an autonomous agent studio. Here's how we cut the bill ~90%.
We run a studio where AI agents work mostly unattended — they write code, ship sites, produce...
How to Build a High-Performance RAG Pipeline with Ollama, Python and TypeScript
The TL;DR If you need to spin up a local, privacy-first AI agent that can query your own...
Everyone says their agent "has memory"
Everyone uses the word "memory" but I feel like they all mean something different by it. For some...
I built a 3B lease risk scanner that runs without an external LLM API
Lease Lens is a Hugging Face Build Small Hackathon project: a fine-tuned Llama 3.2 3B model for grounded lease risk review.
I stopped telling ChatGPT to 'fix it.' Here's the 4-part prompt I use instead.
For about a year I used AI to code like a slot machine. Paste a wall of code. Type "fix it" or "make...
The Rule Held. The Boundary Moved Up. AI Memory Judgment, CLAIM-31: Verified Carryover Across Closes
In my last claim, a sequence got allowed that probably should have made you nervous. Thirteen...
Microsoft AI Agent Architecture in 2026: A Decision Framework for Copilot Studio, Foundry, Agent Framework, and Logic Apps
Stop Picking AI Frameworks Before You Answer This One Question If you're building AI...
Samiksha AI: Universal Review & comment Analyzer
Hey DEV Community! I recently participated in a hackathon and built Samiksha AI, a universal review...
6 months later: Apple Finally Shipped Local Multimodal in Xcode 27 Beta
A while ago I wrote a full llama.cpp iOS implementation using Obj-c bridge because I wanted one...
We Built a Self-Hosted AI Platform That Runs 100% on Your Hardware — Introducing local-ai.run
TL;DR: local-ai.run is a free, open-source, self-hosted AI platform. Chat with your files, generate...
Making a fleet of self-hosted LLM agents trustworthy
Running one local LLM node is easy. Running a fleet of them, off-cluster, and trusting it to stay current and stay honest, is the hard part. This is the work that got LLMKube there...