Technical articles, tutorials, and deep dives.
Keeping a credential out of an LLM's context is necessary but not sufficient. The design I am building toward, the boundary that already holds, and the harder one that is still open: keeping the secret away from code the model can run.
Why long-running agent tasks die on restart, and how to model delegation as a durable state machine on a message bus: one persisted event per transition, no polling, resume from the last recorded state.
Mutable agent memory loses provenance and makes deletion a hope. Modeling memory as an append-only log where state is a fold that reads only the log makes erasure structural: remove the source events, re-fold, and nothing survives.
Why point-to-point integration glue grows multiplicatively, how a canonical model turns it into addition, and why the authoring tooling is where the real leverage lives.
How I use Herdr Annotations to select exact lines from an agent's plan, attach focused comments, and send a coherent review back in one prompt.
How I built a Herdr plugin for reusable S3-backed image URLs—and where Herdr's native remote image paste is the better tool.
A quick guide to optimizing zsh configuration for faster terminal startup using lazy loading and removing dead code.
Learn how to deploy autonomous AI coding agents on Cloudflare's edge infrastructure with OpenHands. Complete guide with SDK, examples, and deployment instructions for building AI-powered developer tools.
A deep dive into how I built this website using Astro, Tailwind CSS, and Markdown. We'll cover content collections, view transitions, and more.