Writing
Long-form notes on agents, generative UI and the systems underneath, each written up with working code.
- No. 08 Edge & platform
Building dockyard: A Zero-Dependency Docker Dashboard for Developer Machines
Twenty plus containers on one dev box, and an AI agent that starts a new one per chat. A small zero-dependency dashboard for the question that actually matters: what is this container logging right now?
#docker#developer-experience#claude#devtools#ai-agents - No. 07 Generative UI
Painting Widgets Token by Token: Building Claude-Style Generative UI from Scratch
The follow-up to reverse-engineering Claude's visualizer: a from-scratch implementation with a Pi agent server, visual tools, a sandboxed iframe widget manager, and a postMessage RPC bridge. Watch html widgets paint token by token as the model streams a tool call. Full code, no framework.
#claude#agent#ai#iframe#sandbox#postmessage#visualizer#tutorial#typescript - No. 06 Agents & MCP
Wiring Feedback Loops Into Agent Skills
AI agent skills are static by default — instructions that never learn from real usage. Here's a pattern for making skills that improve over time using file-based memory and graduation rules.
#ai#skills#agent-development#developer-tools#claude - No. 05 Agents & MCP
Agent Skills That Grow: The Wrapper Pattern for Minting New Scripts
Most skills ship with a fixed set of scripts. Here's a pattern that lets the agent create new scripts on the fly, using wrapper libraries as building blocks.
#ai#skills#agent-development#developer-tools#claude#extendable-skills#self-expanding-skills - No. 04 Generative UI
Reverse-Engineering Claude's Inline Diagrams: An Architecture Deep Dive
How Claude renders inline-diagrams in chat - A deep dive into Claude's visualizer, the system that turns 'draw me a diagram' into interactive iframes with sandboxes, postMessage bridges, and the MCP Apps specification.
#claude#agent#ai#mcp#mcp-apps#architecture#iframe#sandbox#visualizer#design-system - No. 03 Agents & MCP
Building an In-house MCP Server for Code Reviews: Lessons After One Year
What we learned building and running a local MCP server for code reviews—from fighting AI-generated code bloat to integrating organizational context. Built with Claude Code CLI.
#ai#code-review#mcp#claude#developer-experience - No. 02 Go services
Building a High-Performance Image Resizer Proxy with Go
Learn how to build a containerized image resizing service using Go and libvips for on-demand image optimization with S3 caching.
#go#microservices#docker#image-optimization - No. 01 Article
Decorator-Based Selective Loader for Angular HTTP Requests
Learn how to implement a selective page-level loader for specific HTTP requests in Angular using decorators. Control which requests show loaders without cluttering your code.
#angular#typescript#decorators#http