The Agent Runtime Should Not Own the Product
A Hermes personal shopper exposes a durable architecture boundary: the agent runtime may produce decisions, but canonical product state needs a life outside it.
Tag
Agentic Engineering
Articles connected by a shared topic.
Articles
Memory Is Not State
Agent memory is a scoped service layer, not runtime state owned by an agent instance.
A Working Agent Is Not a Working Factory
How to test whether a layered agentic workflow preserves context, responsibility, verification, and recovery for a solo developer.
An Agentic Factory Is an Architecture, Not a Tool Stack
Why an agentic factory is an architecture of responsibility, evidence, and boundaries—not a stack of tools or a more powerful coding agent.
Working Is Not a Quality Metric
Why producing working code faster with AI raises the stakes on architectural quality, and why passing tests is not the same as having sound boundaries.
OpenSpec Optimizes Chaos, Not Tokens
Why OpenSpec belongs in a different category than knowledge tools—and why planning before execution is the actual constraint it addresses.
Local Knowledge Beats Always-On Tools in AI-Assisted Development
Why the biggest gain in AI-assisted development comes from durable local knowledge and disciplined workflow structure, not from keeping every external tool always active.
The Problem Is Not Prompting. It Is Context Decay.
Why AI-assisted development breaks down when useful reasoning disappears between sessions, and why durable project context matters more than clever prompts.
Planning Is Where AI Work Becomes Reviewable
Why planning is less about agent autonomy and more about making AI-assisted work inspectable before it becomes expensive.
Agent Tools Need Product Design Too
Why agent tools are control surfaces for safe, reviewable loops—not just callable functions.