Articles

Practical AI engineering. Lessons from production, things that work, things that don't.

• The Knowledge Rancher

  When generation becomes free, the job stops being production and turns into managing a herd you didn't have to raise. What's left is judgment and timing, and that drains you in a way typing never did.

  May 29, 2026

• MCP Apps: When Your Server Needs a Face

  MCP Apps let servers render interactive UI directly in conversations. The interesting question isn't how. It's when you should bother.

  May 23, 2026

• Writing a Good MCP Server

  Most MCP servers expose too many tools with bad names and useless errors. Practical lessons from building servers that models actually use well.

  May 12, 2026

• Intro to Claude Context

  Claude starts every conversation as a blank slate. Context tiers let you fix that once instead of fixing it every time you open a chat.

  May 8, 2026

• Prompted but Not Read

  We used to write 'Dictated but not read' at the bottom of letters when a secretary did the typing. The parallel to what we're all doing now is too perfect to ignore.

  May 4, 2026

• Toxic AI Mentality

  A frame people fall into where AI failure becomes a trophy. The screenshot is queued before the prompt is sent. Meanwhile, everyone around them is shipping.

  May 2, 2026

• We Automate What We Can Verify

  Code was the first big win for AI agents because code is cheap to check. The same rule decides which business processes compress next, and which stay stuck.

  May 2, 2026

• What 'Giving Data to AI' Actually Means

  The mental model is wrong. You don't pour your database into a prompt. You equip the model to go look, and that's the project every business is actually working on.

  Apr 27, 2026

• Don't Distract the Model

  Packing competing objectives into one prompt costs quality on both. The intuition for when to split is a real skill.

  Apr 22, 2026

• Using AI Is Management

  People who've managed teams tend to get more out of AI faster. The skills transfer directly: delegate clearly, define success, don't blame the team member for your assignment.

  Apr 22, 2026

• Stop Micromanaging the Model

  Modern LLMs are capable enough that step-by-step instructions constrain them. Specify what done looks like, not how to get there. Declarative beats imperative.

  Apr 20, 2026

• The English Trap

  You're not having a conversation with an LLM. You're writing a spec for a system that will exploit every ambiguity you leave on the table. The sooner you treat it that way, the sooner your results stop being wildly inconsistent.

  Apr 20, 2026

• Agents Are About Correction

  AI with tools can act. What makes an agent different is what happens when the action fails.

  Apr 17, 2026

• Don't Use Model Outputs in Production

  When you pipe LLM chat responses into production systems, you're using a scratch channel as a delivery mechanism. Tool calls separate reasoning from output and fix the reliability problems you didn't know you had.

  Apr 16, 2026

• GitHub Copilot CLI Is a Hidden Gem

  I use Claude Code and Codex daily. My instinct was to recommend them to my son. I was wrong.

  Apr 10, 2026

• MCP Is the OAuth Layer

  The anti-MCP take is a single-user take. When your agent serves multiple users accessing their data on remote services, you need a protocol. MCP is the one.

  Apr 3, 2026

• Why Emphasis Works in Prompts

  Bold text and CAPS in prompts aren't voodoo. They work because of how attention literally functions in transformers. Understanding the mechanism makes you a better prompt engineer.

  Mar 27, 2026