Trajectory Lab: Scoring Structure, Not Length
I argued that the structure of an agent run beats its length. Then I built a tool to measure it, and won't ship it until the central claim is proven. Here's the build, and the gap.
agentic-ai
6 posts
11 min read
Scaffolding Over Horsepower: Subagents, Skills, Hooks, and MCP
A working developer's guide to subagents, skills, hooks, and MCP. And the discipline of adding a block only when you can name the failure it prevents.
Design Before Code: A Discipline for AI-Assisted Engineering
When AI writes the code, the reasoning that produced it never exists anywhere except in a transient context window. A two-session pattern (a long Workshop to build the design, and a series of fresh Cold Reads to test it) moves accountability back where it belongs.
Agentic UI: When AI Stops Talking and Starts Doing
The shift from conversational to agentic interfaces, and what it means for frontend architecture.
The LLM Agent Debugging Problem: Building Observability from Scratch
A practical guide to debugging LLM agents, with structured logging utilities, trace visualization components, and replay infrastructure you can steal for your own projects.
Building Private & Offline LLM-Powered Experiences: Client-Side AI Agents with Wasm
Learn how to build browser-based AI agents that run entirely on the client side using WebAssembly. This guide covers implementing a RAG system with local LLM inference for private, offline-capable applications.