Operating manual
Tag: ai-agents
A focused reading path for ai-agents: related field notes, evidence trails, and operating questions from the archive.
- green-status-is-not-shipped-work.md
Green Status Is Not Shipped Work
Agent workflows need deliverable-level acceptance tests because internal completion state is not the same thing as user-facing proof.
open artifact → - protocols-make-agent-exchange-legible-governance-still-lives-above-the-protocol.md
Protocols Make Agent Exchange Legible. Governance Still Lives Above the Protocol.
A2A and MCP make agent exchange easier to standardize, but they do not decide authority, review, provenance, memory, escalation, or accountability.
open artifact → - your-ai-shouldnt-be-one-assistant-it-should-be-a-room-full-of-desks.md
Your AI Needs a Room of Desks
One generalist assistant is the wrong unit of deployment. The right unit is a small, named fleet — each desk owns a queue, a memory, and a hand-off. Operator sits in the loop.
open artifact → - the-personal-ai-os-wont-be-a-chatbot-it-will-be-a-continuity-layer.md
The Personal AI OS Won't Be a Chatbot. It Will Be a Continuity Layer.
Agents are becoming abundant. The scarce platform is the continuity layer that carries goals, memory, permissions, workflow state, and verified outcomes across apps, devices, agents, APIs, and humans.
open artifact → - the-memory-problem-why-ai-agents-forget-your-preferences-between-sessions.md
The Memory Problem Why AI Agents Forget Your Preferences Between Sessions
Discover why AI agents restart context between sessions and how persistent memory systems solve this critical workflow challenge.
open artifact → - the-end-of-platforms-what-happens-when-every-app-becomes-an-agent.md
The End of Platforms What Happens When Every App Becomes an Agent
Discover how AI agents are replacing traditional apps in the post-platform internet. Learn what this shift means for users, developers, and the future of digital products.
open artifact →