agent-workflow
Articles
You Cannot Instruct an Agent Not to Leak
Memory notes told the agent not to echo secret values. It did anyway, twice. The fix was structural enforcement at the tool boundary, not better instructions.
A Design System Sized for One Operator and a Team of Agents
Multiple ventures, one tokens package, three brownfield migrations, a CI gate, and the GA cut. What we built when the conventional playbook did not fit.
When a Behavioral Reflex Becomes a Slash Command
A directive repeated enough times got shipped as a skill. When that is the right call, and when memory or CLAUDE.md would have been the wrong tool.
Agents Building UI They Have Never Seen
Seventeen PRs, three editor panels, a navigation redesign, and 40 hours of agent time. The human directing the work has never opened the app in a browser.
Design Specs as Agent Infrastructure
Agents building UI from text descriptions produce divergent implementations. Design specs loaded at startup solved this.
A Design Tool Bake-Off - Figma MCP vs Google Stitch
We tested Figma MCP and Google Stitch head-to-head on the same three UI panels. Sixty API calls versus three.
From Zero to Landing Page in Four Days
A new venture went from repo creation to production-ready Astro site with 46 merged PRs in four days. The infrastructure did most of the work.
From Code Review to Production in 48 Hours
How AI agents executed a full product sprint - from code review through production deploy - in 48 hours for a writing app.
Finding Four Auth Vulnerabilities in One Code Review
How AI-generated prototype code accumulates auth debt and how one code review session catches it systematically.
Secrets Management for AI Agent Teams
How to manage secrets across projects, machines, and autonomous agents without .env files, hardcoded credentials, or accidental exposure.