Notes from building software, leading teams, and working with AI.
From the workbench.
Things I have built.
Things I have learned.
Things I am figuring out.
I ran 25 models through eight business briefs, with and without my anti-slop rules. GPT-6 Astra was the best and least sloppy in my limited runs. The whole thing is open source, and I am asking someone to make it a real benchmark.
My starting proposal for Attention-First Engineering: Day and Week outcomes, configurable daily ticket capacity, and human ownership of intent, understanding, and acceptance.
What I learned moving email classification from language models to Jev: fast typed decisions, imperfect eval results, and a tradeoff I am willing to try.
How I am using Grok Bot, external search, and specific feedback to explore ideas. Includes a starter prompt, a worked example, and checks for memory and repetition.
What is an agent harness? Learn how it works, build a custom support agent with Vercel AI SDK, and compare Sol and Luna with a runnable eval suite.
My experience with GPT-6 Astra and Claude Fable for research, proposals, and consulting: both are smart enough. I want the same intelligence cheaper and faster.
Open-source adversarial review for code and business work with Friendly Adversary and Zero Defect across Claude Code, Codex, and Claude Cowork.
A practical debugging writeup on getting the unofficial Linux Codex Desktop App remote control flow working so Linux can control a Mac mini.
CLAUDE.md is directory-scoped. .claude/rules/ is pattern-scoped. Most teams only use CLAUDE.md and miss the rules mechanism entirely. Here is how we use both in a real Nx monorepo.
Azure Entra ID breaks the MCP auth spec in at least 10 ways. Here is every error code, every workaround, and the OAuth proxy pattern that makes it all work with Claude Code, MCP Inspector, and other MCP clients.
PBC v2.0 simplifies the Claude Code plugin, moves commands to skills, drops named agents, adds grill-me and handoff, and now has a Codex version too.
I got the AI deployment gap right and the job title wrong. The market has converged on Forward Deployed Engineer, a role built on full-stack engineering, client-facing consulting, and AI-native delivery.
Step-by-step guide to building an MCP server on NestJS with Auth0 OAuth and Azure AD SSO. Fixes the AADSTS9010010 resource parameter error without a gateway, proxy, or dynamic client registration.
A practical guide to running Qwen 3.5 9B Uncensored as a local model on a single RTX 3090 or RTX 4090 with llama-server, then wiring it into OpenCode.
A practical, layered blueprint for making your web app easy for AI agents to discover, understand, and safely act on.
I open-sourced my Claude Code plugin that runs a 4-step pipeline: Research, Plan, Implement, Review. It uses Opus for orchestration and Codex for implementation, with independent review loops and full traceability.
A practical guide to the 3-tier documentation architecture that makes AI coding agents work: root CLAUDE.md, task-specific skills, and agent guides with progressive disclosure.
A practical update on my early 2026 workflow with OpenCode and Claude Code, including Ralph loops, human gatekeeping, and reusable agent skills.
OpenCode and other AI tools are requesting text/markdown by default. Here's why you should support Accept headers for better AI agent compatibility.
My experience switching from Cursor to Claude Code Max and OpenCode, and how it transformed my development workflow while building an AI Agent Platform.
Everything that broke (and how I fixed it) while wiring Google’s image model into a full-stack agent platform: streaming, message conversion, file handling, and shipping images without melting your browser.
Dex from HumanLayer outlines 12 essential principles for building reliable AI agents. These best practices resonated deeply with my own agent development experience.
How and why I combine Pydantic AI with Vercel AI SDK to build AI agents. Learn to connect Python Pydantic AI backends to TypeScript frontends with streaming, tool calling, and MCP servers. Example GitHub repo included.
Learn how to create a complete MCP server in a single TypeScript file using Bun. This tutorial shows you how to wrap the Petfinder API with OAuth authentication, making it perfect for both humans and LLMs to understand and modify.
My recommendations for tech stacks that work well with LLMs: React (Vite/Next), TypeScript, Python, Tailwind, Shadcn, and Ruby on Rails.
Overview of the Jira “Agent Flayer” attack and practical steps: disable auto-run, inventory/approve MCP servers (e.g., Atlassian MCP), avoid untrusted ticket routes.
A quick demonstration of how sometimes GPT-5 needs a little encouragement to follow instructions properly.
Practical recommendations for working with Agentic Coding Assistants code effectively in August 2025: planning with GPT-5, when to code with GPT-5 vs Claude, watching chain-of-thought, and choosing stable tech.
Early notes from using GPT-5 in Cursor: stricter user rules needed and performance tradeoffs between default and fast modes.
OpenAI launches GPT-5 with 400K context window, competitive pricing, and claims to be the best coding model today. Here are the key highlights and comparisons with Anthropic's offerings.
Learn how to leverage reasoning models like o1 or o3-mini to generate comprehensive PRDs and automatically convert them into actionable GitHub issues.
How to effectively combine o3-mini and Claude 3.5 Sonnet in Cursor for optimal coding workflow.
My experience running the DeepSeek R-1 distilled Qwen 32B model locally on a single RTX 4090, and how it compares to cloud-based alternatives.
Understanding the performance gap between distilled and full versions of DeepSeek R1, and why it matters.
Major shifts in U.S. AI policy and a massive new infrastructure investment signal changing priorities in artificial intelligence development.
What will be the hot AI topics in 2025?
Meta released Llama 3.2 and its ready for edge and mobile devices, along with a new vision model.
Learn how to efficiently balance traditional coding with the use of Large Language Models (LLMs) to solve problems effectively. Discover strategies to optimize processes like web scraping, saving time and resources by knowing when to code and when to leverage AI.
Getting a Cypher Query from an Article using a Large Language Model.
I will explain how and why I use Groq and Llama 3.1 to extract insights from articles.
Comparing Ollama w/ Mixtral vs GPT-4 vs Claude 3 Opus for my command line application SALTE: Semi-Autonomous Linux Task Executor
Being smart about how we ingest PDFs is crucial. Here's how I used OpenAI's GPT-4 Vision to convert them to Markdown.
Here's how I crafted a Typescript NPM package with Bun called Function Agents.
Explore how the synergy of Azure Functions, Node.js, and OpenAI's GPT-4 can revolutionize email customer support. Dive into the step-by-step process of building a responsive AI Customer Service Agent.
A code example of how to use the new Chat Completion Function Calling API with JavaScript (Bun and Express)
I made an npm package called next-rails that gives the power and syntax of the Rails CLI to Next.js applications.
Learn how to create a chatbot with OpenAI, Next.js, and Postgres for free.
Learn how to store and query your own data using OpenAI Embeddings and Supabase
In this post, I introduce next-rails, a new npm package I developed to bring the efficiency of Rails-like features to Next.js, aimed at improving your full-stack development experience.
By taking full advantage of generous free tiers of cloud services, you can run a scraping hub for under $10 a month.
How and why I made a scraper with Cloudflare Workers and OpenAI's API
How I made a web scraper using a React Server Component in a Next.js app.
Prompting ChatGPT to help me create a Live Estimation App with Next.js and Supabase.
Prompting ChatGPT to help me create a Live Estimation App with Next.js and Supabase.
Interact with OpenAI's GPT-4 model directly from your bash terminal for quick answers to your questions.
An advanced Git hook solution for monorepos, similar to Husky.
useMemo, useState, useEffect, and useReducer are all you need to eliminate all unnecessary rerenders in React.
How I revived a four-year-old React Class Component and turned it into a React Hook.
Explaining step by step how to make a GraphQL API with Ruby on Rails.
Learn how I built a GPT Test Generator Bun app with ChatGPT.
Copying and pasting to ChatGPT to generate Cypress Component Tests.
Apollo Server used to be exclusive to Node.js, not anymore. Here's how to make an Apollo Server with Bun.
Express used to be exclusive to Node.js, not anymore. Here's how to make an Express Server with Bun.
Using Honojs with Bun to host a GraphQL Server.