TEDWARD.NET · A WEEKLY DEV BLOG BY TED WARD
Dispatches from the sharp end of AI & software.
SHOWING 7 / 61 DISPATCHES — TOPIC: ALL
ALL 61 POSTS ↗
The Great Context Trap: Why Your AI Memory is Broken (And How to Fix It)
We are bleeding our project context to cloud providers every time we open a new chat window. Discover how the Foundry ecosystem and the Model Context Protocol enable portable, sovereign AI memory that finally puts you back in control.
The Word for AI's Worst Output Is Slop
Code that works but is structurally wrong is the silent killer of AI-assisted projects. Discover how moving from prompt-based instructions to governance-as-a-service, or the Foundry, eliminates AI-generated slop.
A Portfolio That Grew Into a Blog: Rebuilding on Next.js
Discover how I transformed my static portfolio into a server-side rendered blog using an AI-orchestrated fleet. I detail the architecture, the governance layer, and the surprising economic reality of using multi-agent workflows for framework migrations.
From Dashboard to Dispatch: Redesigning tedward.net
After a year of 'temporary' design, tedward.net has been completely rebuilt from the ground up. This redesign moves away from the static dashboard model to an editorial-first platform that reflects my weekly focus on AI engineering.
The Foundry Update: Architecting Multi-Agent Intelligence
After a total overhaul of The Foundry, I am shifting my strategy. By focusing on granular model selection and graph-based codebase management, I am prioritising organic adoption over a premature public release.
Knowing When to Fold: Why I'm Shutting Down Vyzo
Shutting down a project is never easy, but it is a vital part of the development lifecycle. Today I am reflecting on why I am sunsetting Vyzo, from the challenges of platform monopolies to the harsh economics of LLM API costs.